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

    Neuronpedia

    INDEX
    Explanations

    tokens or sequences indicating structure or formatting in code

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

    code structures and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfectos
    -0.45
     abuelos
    -0.40
     referrerpolicy
    -0.38
     recours
    -0.37
    TypedDataSet
    -0.36
     ideales
    -0.36
    PerformLayout
    -0.36
     parfaite
    -0.35
     jugé
    -0.34
     perfecta
    -0.34
    POSITIVE LOGITS
    MessageOf
    0.86
    eraard
    0.57
     @"/
    0.57
    SourceChecksum
    0.55
    EDEFAULT
    0.54
     AssemblyTitle
    0.50
    èlement
    0.50
    opoly
    0.49
    pty
    0.47
    buttonBar
    0.47
    Act Density 0.361%

    No Known Activations