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

    Neuronpedia

    INDEX
    Explanations

    soliciting feedback

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ありがとうございます
    -0.07
     looks
    -0.07
     suits
    -0.07
    くらい
    -0.07
     организации
    -0.06
    ให
    -0.06
    _visitor
    -0.06
     psychologically
    -0.06
     pepp
    -0.06
    霸气
    -0.06
    POSITIVE LOGITS
    垂
    0.07
    ้น
    0.07
    튱
    0.07
     Mostly
    0.06
     anarchists
    0.06
     assertion
    0.06
    ients
    0.06
     estimator
    0.06
     Bản
    0.06
     picker
    0.06
    Act Density 0.000%

    No Known Activations