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

    Neuronpedia

    INDEX
    Explanations

    mathematical/logical structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isto
    -0.06
    	Value
    -0.06
     imprisonment
    -0.06
     Duty
    -0.06
     pca
    -0.06
     xc
    -0.06
    _cats
    -0.06
    Fuck
    -0.06
     Leading
    -0.06
     Hole
    -0.06
    POSITIVE LOGITS
     дви
    0.06
    通过
    0.06
     встанов
    0.06
     unanimously
    0.06
     windy
    0.06
    acher
    0.06
     tarım
    0.06
    .published
    0.06
     mettre
    0.06
    Verb
    0.06
    Act Density 0.049%

    No Known Activations