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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nearly
    -0.07
    xffffff
    -0.07
     Arial
    -0.06
    ulong
    -0.06
    .Cookies
    -0.06
     трав
    -0.06
     Hussein
    -0.06
    �
    -0.06
    {EIF
    -0.06
    )+'
    -0.06
    POSITIVE LOGITS
     boots
    0.07
     признач
    0.07
     Boots
    0.07
     ش
    0.07
    (ws
    0.06
    LEFT
    0.06
     adjusted
    0.06
    ειτουργ
    0.06
    kola
    0.06
    	dp
    0.06
    Act Density 0.000%

    No Known Activations