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

    Neuronpedia

    INDEX
    Explanations

    ace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \model
    -0.06
    ้บร
    -0.06
    classmethod
    -0.06
     Johann
    -0.06
     manner
    -0.06
    Saturday
    -0.06
     Nepal
    -0.06
     Grandma
    -0.06
     недели
    -0.06
     Far
    -0.06
    POSITIVE LOGITS
    aces
    0.09
    ce
    0.09
    ç
    0.08
    ace
    0.08
    ices
    0.08
    áce
    0.08
    �
    0.07
    CE
    0.07
    aced
    0.07
     brace
    0.07
    Act Density 0.027%

    No Known Activations