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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    es
    -0.06
     освіти
    -0.06
    endez
    -0.06
     خور
    -0.06
    structor
    -0.06
    emm
    -0.06
     وقتی
    -0.06
    نگ
    -0.06
    ืน
    -0.06
     vaping
    -0.06
    POSITIVE LOGITS
    ::{
    0.07
    _GO
    0.07
    .${
    0.07
    backup
    0.06
    .grpc
    0.06
    \Component
    0.06
     DISP
    0.06
    ={['
    0.06
     carrot
    0.06
     asteroid
    0.06
    Act Density 0.044%

    No Known Activations