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

    Neuronpedia

    INDEX
    Explanations

    question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ENCODE
    -0.07
     intention
    -0.07
    Timeout
    -0.07
    Markup
    -0.06
    Analyzer
    -0.06
    _that
    -0.06
     UNION
    -0.06
     Teaching
    -0.06
     mondo
    -0.06
    층
    -0.06
    POSITIVE LOGITS
    今日
    0.07
    094
    0.06
     soci
    0.06
    -beta
    0.06
     ApiController
    0.06
    apes
    0.05
     Jupiter
    0.05
    uen
    0.05
    -strokes
    0.05
     MPG
    0.05
    Act Density 0.026%

    No Known Activations