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

    Neuronpedia

    INDEX
    Explanations

    funding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Κά
    -0.07
    Positive
    -0.07
    contr
    -0.07
    GPU
    -0.07
     svou
    -0.06
    _kv
    -0.06
    わり
    -0.06
     jeszcze
    -0.06
    ziej
    -0.06
    Γ
    -0.06
    POSITIVE LOGITS
    هدف
    0.07
    -character
    0.07
    (food
    0.07
     Sonic
    0.07
     Corvette
    0.06
     замов
    0.06
    essel
    0.06
    (Job
    0.06
    =function
    0.06
    ollywood
    0.06
    Act Density 0.012%

    No Known Activations