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

    Neuronpedia

    INDEX
    Explanations

    present participle verbs/gerunds

    oai_token-act-pair · gemini-2.0-flash

    looking, going

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -0.97
    Tikang
    -0.94
     Roskov
    -0.88
    المناصب
    -0.86
     Мексичка
    -0.85
    хьтан
    -0.84
     looking
    -0.79
    OGND
    -0.79
     Exactos
    -0.79
     nakalista
    -0.77
    POSITIVE LOGITS
    ”
    0.53
     Stay
    0.52
    ung
    0.51
    ล
    0.51
     When
    0.51
    nders
    0.51
    ori
    0.50
    "
    0.49
    .”
    0.48
    When
    0.48
    Act Density 1.658%

    No Known Activations