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

    Neuronpedia

    INDEX
    Explanations

    Institutional history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    犬
    -0.07
    lip
    -0.07
    ляються
    -0.06
     moż
    -0.06
    _cod
    -0.06
    translations
    -0.06
    ensen
    -0.06
    /scripts
    -0.06
    th
    -0.06
    ают
    -0.06
    POSITIVE LOGITS
     Classics
    0.07
     trình
    0.07
     DEFINE
    0.07
     Beautiful
    0.07
    termin
    0.06
    @Injectable
    0.06
    (**
    0.06
     solemn
    0.06
     succeeds
    0.06
     Typed
    0.06
    Act Density 0.040%

    No Known Activations