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

    Neuronpedia

    INDEX
    Explanations

    非常

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sini
    -0.09
     tahan
    -0.08
    materiaal
    -0.08
     воз
    -0.08
     fidèle
    -0.08
    adikan
    -0.08
     perseverance
    -0.08
    имого
    -0.08
     аккумуля
    -0.08
    Воз
    -0.08
    POSITIVE LOGITS
     violate
    0.08
     copyrighted
    0.08
    _keywords
    0.07
     questionable
    0.07
    ീന
    0.07
    典
    0.07
     couch
    0.07
     confusing
    0.07
    Instr
    0.07
    conference
    0.07
    Act Density 0.001%

    No Known Activations