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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    った
    -0.07
    _sz
    -0.07
     spielen
    -0.07
    刷新
    -0.07
    _poly
    -0.07
    а
    -0.07
    ibling
    -0.07
    钍
    -0.07
    觸
    -0.07
    _unref
    -0.07
    POSITIVE LOGITS
     testimon
    0.07
    .lot
    0.06
    โปรโม
    0.06
     demonstr
    0.06
    ewire
    0.06
     gele
    0.06
    텃
    0.06
     soc
    0.06
     med
    0.06
     recom
    0.06
    Act Density 0.000%

    No Known Activations