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

    Neuronpedia

    INDEX
    Explanations

    Broad topics and feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SEA
    -0.07
    TJ
    -0.07
    JJ
    -0.07
    URY
    -0.07
    being
    -0.06
    uds
    -0.06
    uru
    -0.06
     SY
    -0.06
    ,J
    -0.06
     Established
    -0.06
    POSITIVE LOGITS
    .
    0.09
    0.09
     (
    0.08
    :
    0.07
     дра
    0.07
    -initialized
    0.06
    .↵
    0.06
     Enumerable
    0.06
     fat
    0.06
    	Common
    0.06
    Act Density 3.945%

    No Known Activations