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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expanded
    -0.09
     anal
    -0.09
     expanded
    -0.09
     Sheffield
    -0.08
    Lu
    -0.08
     weight
    -0.08
    taa
    -0.08
     expands
    -0.07
    нулся
    -0.07
    rightness
    -0.07
    POSITIVE LOGITS
     その他
    0.11
    その他
    0.10
     기타
    0.09
     الأخرى
    0.08
    _other
    0.08
    <i
    0.07
     уст
    0.07
     અન્ય
    0.07
    _Data
    0.07
     неп
    0.07
    Act Density 0.002%

    No Known Activations