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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HttpResponse
    -0.07
     الس
    -0.06
    iani
    -0.06
    _TYPES
    -0.06
     subscribing
    -0.06
     owing
    -0.06
     teas
    -0.06
     prix
    -0.06
     필요
    -0.06
    ,+
    -0.06
    POSITIVE LOGITS
     MPL
    0.07
    	fd
    0.06
    reducers
    0.06
     ACLU
    0.06
    .Cdecl
    0.06
     Breaking
    0.06
    ><
    0.06
     Theta
    0.06
    mlx
    0.06
     uchar
    0.06
    Act Density 0.379%

    No Known Activations