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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AppComponent
    -0.07
    accessible
    -0.07
     земель
    -0.07
    ял
    -0.07
     Parcelable
    -0.06
    نين
    -0.06
    agu
    -0.06
    ivan
    -0.06
    \Plugin
    -0.06
    ActiveSheet
    -0.06
    POSITIVE LOGITS
     tossed
    0.06
    (add
    0.06
     xhttp
    0.06
     did
    0.06
    ischen
    0.06
    Demon
    0.06
    ..:
    0.06
    standen
    0.06
     helt
    0.06
    彡
    0.06
    Act Density 0.040%

    No Known Activations