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

    Neuronpedia

    INDEX
    Explanations

    a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.62
     appellant
    1.33
     ONU
    1.27
     TBS
    1.24
     ills
    1.16
     notary
    1.16
     PTA
    1.15
     appellants
    1.14
     パーカー
    1.13
     OTS
    1.13
    POSITIVE LOGITS
    m
    1.77
    c
    1.73
    و
    1.57
    รษฐกิจ
    1.46
    ુ
    1.44
    itectura
    1.43
    رف
    1.41
    ري
    1.40
    motor
    1.40
    mile
    1.38
    Act Density 0.181%

    No Known Activations