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

    Neuronpedia

    INDEX
    Explanations

    ino

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "For
    -0.06
     zum
    -0.06
     referral
    -0.06
    Instr
    -0.05
     kadın
    -0.05
     fou
    -0.05
    ynı
    -0.05
    inho
    -0.05
    iteli
    -0.05
     princes
    -0.05
    POSITIVE LOGITS
    _GT
    0.07
    キング
    0.07
    řím
    0.07
    government
    0.07
    oly
    0.07
     paramMap
    0.07
    丹
    0.07
    Latch
    0.07
    _coll
    0.07
    avigator
    0.06
    Act Density 0.000%

    No Known Activations