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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMPTY
    -0.07
     Copy
    -0.07
    �
    -0.07
     умов
    -0.06
     kindergarten
    -0.06
     состав
    -0.06
     reforms
    -0.06
     그러
    -0.06
    ंभ
    -0.06
     british
    -0.06
    POSITIVE LOGITS
    #'
    0.07
     Ging
    0.07
    .cost
    0.06
    itchen
    0.06
    requete
    0.06
     люд
    0.06
    sand
    0.06
     Jakarta
    0.06
     hinted
    0.06
     Ост
    0.06
    Act Density 0.158%

    No Known Activations