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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conditional statements and assertions in programming

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

    variable names starting with underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ︎
    -0.41
     Bagian
    -0.40
    ButtonModule
    -0.38
     Hitam
    -0.38
     Перейти
    -0.38
    n
    -0.38
     inoxidable
    -0.38
    hagic
    -0.37
     Lengkap
    -0.37
    FXML
    -0.37
    POSITIVE LOGITS
     (_
    1.77
    (_
    1.45
     [_
    1.37
    [_
    1.36
    >(_
    1.34
    =_
    1.27
     {_
    1.16
    <_
    1.15
     (!_
    1.13
    (&_
    1.10
    Act Density 0.010%

    No Known Activations