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

    Neuronpedia

    INDEX
    Explanations

    journal articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    呼吸道
    -0.08
     insign
    -0.07
     sin
    -0.06
    (commit
    -0.06
     unlink
    -0.06
    .named
    -0.06
     visitors
    -0.06
    ...............
    -0.06
    .getUserName
    -0.06
    .vector
    -0.06
    POSITIVE LOGITS
    찯
    0.08
    -lasting
    0.07
    ocado
    0.07
    —the
    0.07
    另
    0.07
    gende
    0.07
    *j
    0.07
     los
    0.07
    arten
    0.06
    'on
    0.06
    Act Density 0.003%

    No Known Activations