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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     territory
    -0.07
    riages
    -0.06
     rele
    -0.06
     sind
    -0.06
     grape
    -0.06
     этой
    -0.06
     Gut
    -0.06
    หาร
    -0.06
     Hub
    -0.06
     gad
    -0.06
    POSITIVE LOGITS
    gps
    0.08
    -inner
    0.07
    -fontawesome
    0.07
     typeof
    0.06
     statistic
    0.06
     сильно
    0.06
    etc
    0.06
    _params
    0.06
    setText
    0.06
     candy
    0.06
    Act Density 0.004%

    No Known Activations