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

    Neuronpedia

    INDEX
    Explanations

    Legal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mish
    -0.07
     fox
    -0.07
    _buckets
    -0.07
     gamble
    -0.07
    _bins
    -0.06
    FX
    -0.06
     Rhodes
    -0.06
    Segments
    -0.06
    tails
    -0.06
    Fast
    -0.06
    POSITIVE LOGITS
    	vector
    0.07
    ıy
    0.06
    (orig
    0.06
    asuring
    0.06
    .Lines
    0.06
    _REFER
    0.06
     kurul
    0.06
    netinet
    0.06
    #w
    0.06
     помощ
    0.06
    Act Density 0.018%

    No Known Activations