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

    Neuronpedia

    INDEX
    Explanations

    errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lops
    -0.07
     entidad
    -0.07
     застос
    -0.07
    işleri
    -0.06
    ampiyon
    -0.06
     frække
    -0.06
     Elsa
    -0.06
    :update
    -0.06
    ’acc
    -0.06
    Jac
    -0.06
    POSITIVE LOGITS
    ILING
    0.08
     常
    0.07
    total
    0.07
     PAS
    0.06
    має
    0.06
    :void
    0.06
     Rowe
    0.06
     regular
    0.06
     Col
    0.06
    Regular
    0.06
    Act Density 0.253%

    No Known Activations