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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     micro
    -0.07
    cloth
    -0.07
     ^^
    -0.06
    902
    -0.06
    _detection
    -0.06
     favors
    -0.06
     waves
    -0.06
    া�
    -0.06
     grocery
    -0.06
     notes
    -0.06
    POSITIVE LOGITS
    uluğu
    0.06
     Challenger
    0.06
     nouve
    0.06
     tutar
    0.06
    uy�
    0.06
     kanun
    0.06
     Sands
    0.06
     dự
    0.06
    charted
    0.06
     đá
    0.06
    Act Density 0.003%

    No Known Activations