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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hybrid
    -0.07
    gressor
    -0.07
     hashtag
    -0.07
    DG
    -0.07
     عبدال
    -0.07
    Criterion
    -0.06
     categorical
    -0.06
    NP
    -0.06
    Sele
    -0.06
    Ny
    -0.06
    POSITIVE LOGITS
    oust
    0.06
    Have
    0.06
    肯
    0.06
    _TAB
    0.06
    需要
    0.06
    .fire
    0.06
    多
    0.06
     глаз
    0.06
    曾
    0.06
     نخ
    0.05
    Act Density 0.006%

    No Known Activations