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

    Neuronpedia

    INDEX
    Explanations

    collective, ive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hWnd
    -0.07
     scaff
    -0.07
     slope
    -0.06
     Silicon
    -0.06
    .String
    -0.06
    _sta
    -0.06
     можна
    -0.06
     був
    -0.06
    军
    -0.06
    Background
    -0.06
    POSITIVE LOGITS
     collective
    0.17
     Collective
    0.13
     collectively
    0.08
    чины
    0.07
    sil
    0.07
    SHARE
    0.06
    classic
    0.06
    shell
    0.06
    َ
    0.06
     أح
    0.06
    Act Density 0.004%

    No Known Activations