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

    Neuronpedia

    INDEX
    Explanations

    complex situations or regions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mares
    0.64
     الفرق
    0.58
    灸
    0.56
    cept
    0.55
    yourself
    0.55
    zik
    0.55
    テイ
    0.55
    tired
    0.54
    lässlich
    0.54
    recall
    0.54
    POSITIVE LOGITS
     DBMS
    0.62
     Dimension
    0.59
     Bitmap
    0.59
     Irrigation
    0.59
     Sham
    0.58
     Christianity
    0.57
     Supervision
    0.57
    ಙ
    0.57
     Nomination
    0.57
     supervision
    0.56
    Act Density 0.000%

    No Known Activations