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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.76
    CloseOperation
    -0.67
    󠁢
    -0.66
    aarrggbb
    -0.65
     ModelExpression
    -0.64
     يتيمه
    -0.62
    izielle
    -0.62
    fml
    -0.59
     FetchType
    -0.58
    openqa
    -0.57
    POSITIVE LOGITS
    ord
    0.51
    ORD
    0.47
     parity
    0.46
    SetOutput
    0.46
    hode
    0.45
    given
    0.44
    taken
    0.44
     supported
    0.43
    posi
    0.42
    ngua
    0.42
    Act Density 0.000%

    No Known Activations