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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etros
    -0.07
    UTO
    -0.07
     hd
    -0.06
     HD
    -0.06
     Harvard
    -0.06
    endid
    -0.06
     Yug
    -0.06
     프리
    -0.06
     tense
    -0.06
    昭
    -0.06
    POSITIVE LOGITS
     ActionResult
    0.07
     funding
    0.07
    <section
    0.07
     ：
    0.06
     вияви
    0.06
    kin
    0.06
    駅徒歩
    0.06
    unsch
    0.06
     відріз
    0.06
    .colorbar
    0.06
    Act Density 0.001%

    No Known Activations