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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guaranteed
    -0.08
    자의
    -0.06
    (TEST
    -0.06
     insurance
    -0.06
    /context
    -0.06
     Tight
    -0.06
    	hash
    -0.06
     weighs
    -0.05
     franchises
    -0.05
    _BY
    -0.05
    POSITIVE LOGITS
    ract
    0.07
    %)
    0.07
     traged
    0.07
    __(↵
    0.07
    ampa
    0.07
    0.07
    сл
    0.06
     Ebony
    0.06
    ا�
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations