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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (details
    -0.07
     CPU
    -0.06
     Gain
    -0.06
     cpu
    -0.06
    (dw
    -0.06
     fid
    -0.06
     контра
    -0.06
    .net
    -0.06
    MenuStrip
    -0.06
    Agent
    -0.06
    POSITIVE LOGITS
    "(
    0.08
    担
    0.07
    _cross
    0.07
    нар
    0.07
    .',
    0.06
     almond
    0.06
     triggers
    0.06
     concentrates
    0.06
    _normalized
    0.06
    oggle
    0.06
    Act Density 0.051%

    No Known Activations