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

    Neuronpedia

    INDEX
    Explanations

    final

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durumu
    -0.07
    、「
    -0.06
    leyen
    -0.06
    vanced
    -0.06
     пош
    -0.06
     للس
    -0.06
     Fecha
    -0.06
    .""
    -0.06
    房屋
    -0.06
    лату
    -0.06
    POSITIVE LOGITS
    REG
    0.08
     advertis
    0.07
     Ava
    0.07
     brightness
    0.06
    zzle
    0.06
     pretended
    0.06
    _HINT
    0.06
     inspiring
    0.06
    -tooltip
    0.06
    (trigger
    0.06
    Act Density 0.018%

    No Known Activations