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

    Neuronpedia

    INDEX
    Explanations

    missile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accustomed
    -0.08
    [arg
    -0.07
     כשה
    -0.07
     uży
    -0.07
    帮我
    -0.07
     Зна
    -0.07
    .asc
    -0.07
    �
    -0.07
     śc
    -0.07
    (Self
    -0.07
    POSITIVE LOGITS
     permit
    0.07
     stderr
    0.07
    핼
    0.07
    强有力
    0.07
     poisoned
    0.07
    perfil
    0.06
    barcode
    0.06
     disable
    0.06
    Ⲏ
    0.06
     implies
    0.06
    Act Density 0.003%

    No Known Activations