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

    Neuronpedia

    INDEX
    Explanations

    instructions and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claro
    -0.07
    ーロ
    -0.06
    _Edit
    -0.06
    localObject
    -0.06
     Hollande
    -0.06
    .Modules
    -0.06
    ilon
    -0.06
     Import
    -0.06
     celebrations
    -0.06
    UIBarButtonItem
    -0.06
    POSITIVE LOGITS
     generals
    0.07
    .sock
    0.06
    /print
    0.06
    anson
    0.06
     @$_
    0.06
     deze
    0.06
    ़न
    0.06
    爱
    0.06
     قب
    0.06
    幹
    0.06
    Act Density 0.029%

    No Known Activations