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

    Neuronpedia

    INDEX
    Explanations

    Tour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sosyal
    -0.08
    iever
    -0.07
     Franc
    -0.07
    (canvas
    -0.07
    _mini
    -0.06
    recall
    -0.06
    browse
    -0.06
     RUNNING
    -0.06
    .Rec
    -0.06
     اليوم
    -0.06
    POSITIVE LOGITS
     cherished
    0.07
     satur
    0.06
     bolster
    0.06
    lehem
    0.06
     insist
    0.06
    UInt
    0.06
     truncated
    0.06
     paired
    0.06
    miyor
    0.06
     Regulatory
    0.06
    Act Density 0.002%

    No Known Activations