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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    actoring
    -0.07
    elle
    -0.07
    htag
    -0.07
    Highlights
    -0.07
    eligible
    -0.07
     SALE
    -0.07
    ็ง
    -0.06
    uh
    -0.06
     tensions
    -0.06
     watt
    -0.06
    POSITIVE LOGITS
    ді
    0.06
     jumlah
    0.06
    wget
    0.06
    _ent
    0.06
     би
    0.06
    던
    0.06
     craftsm
    0.06
     لإ
    0.06
     downt
    0.06
     시
    0.06
    Act Density 0.036%

    No Known Activations