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

    Neuronpedia

    INDEX
    Explanations

    describing relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    页面存档备份
    0.37
    bruck
    0.37
    XYGEN
    0.35
     kebak
    0.34
    rikes
    0.34
     chargingStation
    0.33
    वत्ता
    0.33
    疑惑
    0.32
    ս
    0.32
    0.32
    POSITIVE LOGITS
    に係る
    0.41
    .,"
    0.38
     impactful
    0.38
    .".,
    0.37
    ，「
    0.37
    makes
    0.36
     entsprechenden
    0.36
     entsprechende
    0.36
     entspre
    0.35
     misfortune
    0.34
    Act Density 0.276%

    No Known Activations