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

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ante
    -0.07
     מסוג
    -0.07
    .Usuario
    -0.07
     donné
    -0.07
    ᑖ
    -0.07
     Tại
    -0.07
     them
    -0.07
    _a
    -0.07
    안내
    -0.07
    acd
    -0.07
    POSITIVE LOGITS
    scale
    0.07
    xE
    0.07
    YELLOW
    0.07
    	RT
    0.07
     Rehab
    0.07
    _CBC
    0.07
    xC
    0.07
     Betting
    0.06
    拥有
    0.06
    ⎢
    0.06
    Act Density 0.002%

    No Known Activations