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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orz
    -0.08
     collo
    -0.08
    诊所
    -0.07
    -AA
    -0.07
     reviews
    -0.07
     Contrast
    -0.07
    _summary
    -0.07
     ♥
    -0.07
    兴旺
    -0.07
     ACCESS
    -0.07
    POSITIVE LOGITS
    latitude
    0.07
    涡
    0.07
    refix
    0.06
    משכנת
    0.06
    榰
    0.06
     creator
    0.06
    占据
    0.06
    .project
    0.06
    骗子
    0.06
     Quantum
    0.06
    Act Density 0.067%

    No Known Activations