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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     greet
    -0.07
    lets
    -0.07
     amid
    -0.06
    ())↵
    -0.06
    月初
    -0.06
     WCHAR
    -0.06
    '],↵
    -0.06
    iddles
    -0.06
     speech
    -0.06
    Initializing
    -0.06
    POSITIVE LOGITS
     tiene
    0.07
     José
    0.07
    _T
    0.07
     tính
    0.07
    �
    0.07
    _DAMAGE
    0.07
    _featured
    0.06
     tranny
    0.06
     gauche
    0.06
     jitter
    0.06
    Act Density 0.056%

    No Known Activations