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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ation/ated"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Consort
    -0.07
     terrible
    -0.07
     lifestyle
    -0.07
     classics
    -0.06
     studios
    -0.06
    벌
    -0.06
    edy
    -0.06
     decreased
    -0.06
     heed
    -0.06
    Scaler
    -0.06
    POSITIVE LOGITS
    _DISPATCH
    0.07
    linked
    0.06
    .isNotEmpty
    0.06
     JsonObject
    0.06
    <QString
    0.06
     amatør
    0.06
     WideString
    0.06
     غ
    0.06
    @Autowired
    0.06
    .hasOwnProperty
    0.06
    Act Density 0.001%

    No Known Activations