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

    Neuronpedia

    INDEX
    Explanations

    building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    394
    -0.08
     dunk
    -0.07
    Stmt
    -0.06
     IRS
    -0.06
     hookers
    -0.06
     Waters
    -0.06
    م
    -0.06
     therm
    -0.06
    Voltage
    -0.06
    225
    -0.06
    POSITIVE LOGITS
     fixation
    0.08
    avě
    0.06
    ενοδο
    0.06
    돌
    0.06
    jur
    0.06
    廷
    0.06
     ''
    0.06
    ”:
    0.06
    »,
    0.06
     розвиток
    0.06
    Act Density 0.019%

    No Known Activations