Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    syntactical elements related to programming constructs such as brackets, semicolons, and whitespace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or configuration file snippets

    np_acts-logits-general · gemini-2.0-flash

    Java and C++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -1.08
    OrBuilder
    -1.02
    migrationBuilder
    -0.77
     nakalista
    -0.75
    }></
    -0.75
     Roskov
    -0.73
     {}));
    -0.73
    __*/
    -0.70
    '])->
    -0.66
    Читати
    -0.66
    POSITIVE LOGITS
    rigkeit
    0.51
     Alors
    0.51
     betweenstory
    0.51
    dbach
    0.51
     GenerationType
    0.51
    nloa
    0.50
    లాలు
    0.49
    UnitTesting
    0.49
    featureID
    0.48
     oreille
    0.48
    Act Density 0.045%

    No Known Activations