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

    Neuronpedia

    INDEX
    Explanations

    references to iterative processes or functions in code

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

    dividing by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeError
    -0.39
     portátiles
    -0.37
     esquerdo
    -0.37
     ***!
    -0.37
     vectorielle
    -0.37
    ValueGenerated
    -0.37
     burbuja
    -0.36
     esquerda
    -0.35
     quizá
    -0.35
     Bucure
    -0.34
    POSITIVE LOGITS
    OGND
    0.57
    redux
    0.52
    Rè
    0.51
    出版年
    0.48
    AnchorStyles
    0.48
     nahilalakip
    0.46
     Roskov
    0.44
    mapStateToProps
    0.44
     kasarigan
    0.43
     PCM
    0.43
    Act Density 0.001%

    No Known Activations