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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ittle
    -0.07
     하지만
    -0.07
     משמעות
    -0.07
    ikit
    -0.07
     vulnerable
    -0.06
    _Value
    -0.06
     grounded
    -0.06
    内容简介
    -0.06
    Hip
    -0.06
     //--
    -0.06
    POSITIVE LOGITS
    聂
    0.08
    宾馆
    0.08
    �
    0.08
     dara
    0.07
    fprintf
    0.07
    行為
    0.07
    _warn
    0.07
     ply
    0.07
    .transfer
    0.07
     engineer
    0.07
    Act Density 0.008%

    No Known Activations