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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     réussi
    -0.07
     assemble
    -0.07
    一枚
    -0.06
    umu
    -0.06
     insulting
    -0.06
    ⟨
    -0.06
    ohl
    -0.06
    倒霉
    -0.06
    立志
    -0.06
    〓
    -0.06
    POSITIVE LOGITS
    bundles
    0.07
    reich
    0.07
     dov
    0.06
    ahrenheit
    0.06
    .IP
    0.06
     intermitt
    0.06
    _beta
    0.06
     mund
    0.06
    招商引
    0.06
    TextBox
    0.06
    Act Density 0.000%

    No Known Activations