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

    Neuronpedia

    INDEX
    Explanations

    Sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     форми
    -0.07
    ....
    -0.07
     محمد
    -0.06
    ██
    -0.06
    mployee
    -0.06
    민국
    -0.06
     facebook
    -0.06
    push
    -0.06
    拼
    -0.06
     CGSizeMake
    -0.06
    POSITIVE LOGITS
    utschein
    0.07
    ｲ
    0.07
    .RES
    0.06
    AppComponent
    0.06
     "#{
    0.06
    quia
    0.06
     lay
    0.06
     Strong
    0.06
     gravel
    0.06
    τρο
    0.06
    Act Density 0.000%

    No Known Activations