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

    Neuronpedia

    INDEX
    Explanations

    lin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harms
    -0.06
     [['
    -0.06
    every
    -0.06
     dotted
    -0.06
    -sup
    -0.06
    writes
    -0.06
    Não
    -0.06
    Las
    -0.06
     leans
    -0.06
    Mapped
    -0.06
    POSITIVE LOGITS
    413
    0.06
    yard
    0.06
    ett
    0.06
    ^
    0.06
    =h
    0.06
     ülk
    0.06
    /tiny
    0.06
     vign
    0.06
     leverage
    0.06
    YA
    0.05
    Act Density 0.000%

    No Known Activations