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

    Neuronpedia

    INDEX
    Explanations

    separate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tre
    -0.07
    anza
    -0.06
    _CBC
    -0.06
    цер
    -0.06
     Dysfunction
    -0.06
     dilation
    -0.06
     strike
    -0.06
    Ber
    -0.06
     balances
    -0.06
    -selling
    -0.06
    POSITIVE LOGITS
     doğal
    0.07
    diği
    0.07
     knowledgeable
    0.06
     Definitions
    0.06
    configs
    0.06
     小
    0.06
     نج
    0.06
    	total
    0.06
     avg
    0.06
     peaked
    0.06
    Act Density 0.009%

    No Known Activations