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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auxiliary
    -0.06
    ансов
    -0.06
     Funeral
    -0.06
    >}
    -0.06
    ising
    -0.06
     Fat
    -0.06
    (response
    -0.06
    Venue
    -0.06
     He
    -0.06
    HT
    -0.06
    POSITIVE LOGITS
    sorry
    0.07
    yth
    0.06
    輯
    0.06
    -save
    0.06
    .ColumnStyle
    0.06
    巧
    0.06
    MethodImpl
    0.06
     برج
    0.06
    岳
    0.06
    _DECL
    0.06
    Act Density 0.018%

    No Known Activations