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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idential
    -0.08
    σή
    -0.08
    ευση
    -0.07
    AttribPointer
    -0.07
     Professionals
    -0.06
    ях
    -0.06
    isle
    -0.06
    籍
    -0.06
     Blink
    -0.06
    uale
    -0.06
    POSITIVE LOGITS
     visita
    0.07
    fois
    0.06
    لاق
    0.06
     zal
    0.06
     kittens
    0.06
     Milli
    0.06
     discord
    0.05
     podría
    0.05
     harus
    0.05
     거래
    0.05
    Act Density 0.000%

    No Known Activations