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

    Neuronpedia

    INDEX
    Explanations

    Technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᾱ
    -0.08
    ╢
    -0.07
    袤
    -0.07
     ure
    -0.07
     tou
    -0.07
    茛
    -0.07
     elder
    -0.07
    <lemma
    -0.06
     chambre
    -0.06
    很漂亮
    -0.06
    POSITIVE LOGITS
    แจ
    0.07
     LGBT
    0.07
    dbc
    0.07
    BuilderInterface
    0.07
    这句话
    0.07
     Dorm
    0.07
    .search
    0.07
     `${
    0.07
    .Command
    0.06
    _submission
    0.06
    Act Density 0.000%

    No Known Activations