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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旧
    -0.08
    LLU
    -0.08
     Having
    -0.07
     kicker
    -0.07
     tighten
    -0.07
     فعل
    -0.07
    귐
    -0.07
    径
    -0.07
    ятся
    -0.07
    겤
    -0.07
    POSITIVE LOGITS
     WiFi
    0.07
     Corinthians
    0.07
     coastal
    0.07
    pheric
    0.06
    (mon
    0.06
    abant
    0.06
    𝙇
    0.06
     Accident
    0.06
    _Offset
    0.06
    ilation
    0.06
    Act Density 0.009%

    No Known Activations