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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to documentation or source code structure

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

    connections between different parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typelib
    -0.52
    DoubleQuotes
    -0.50
    IContainer
    -0.50
     AspNetCore
    -0.46
    vertret
    -0.46
    VersionUID
    -0.45
     defaultstate
    -0.45
    barre
    -0.44
    meg
    -0.44
    itake
    -0.43
    POSITIVE LOGITS
     שוליים
    0.52
     desmotivaciones
    0.52
     szint
    0.52
     either
    0.50
    either
    0.50
     varandra
    0.50
    Either
    0.49
    });
    0.49
     Either
    0.49
     gradova
    0.49
    Act Density 0.656%

    No Known Activations