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

    Neuronpedia

    INDEX
    Explanations

    video games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ras
    -0.06
    incoming
    -0.06
    ैं
    -0.06
    ITES
    -0.06
     vyžad
    -0.06
    DOM
    -0.05
    ARIO
    -0.05
    dom
    -0.05
    _inicio
    -0.05
    istring
    -0.05
    POSITIVE LOGITS
     bitterness
    0.07
    肖
    0.07
    dT
    0.06
    -viol
    0.06
     Align
    0.06
     article
    0.06
     gunmen
    0.06
    ा.↵
    0.06
    ём
    0.06
    天天
    0.06
    Act Density 0.021%

    No Known Activations