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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    溶
    -0.07
    .Tween
    -0.06
     harmless
    -0.06
     Uz
    -0.06
     том
    -0.06
    瀬
    -0.06
    :red
    -0.06
    .compiler
    -0.06
    '=>"
    -0.06
     Jihad
    -0.06
    POSITIVE LOGITS
    parate
    0.07
    oque
    0.07
    getic
    0.07
    (enable
    0.06
    IMUM
    0.06
     Turing
    0.06
    hog
    0.06
    rang
    0.06
     ecosystem
    0.06
    ognito
    0.06
    Act Density 0.000%

    No Known Activations