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

    Neuronpedia

    INDEX
    Explanations

    destroys trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بالٹ
    0.48
    ยายาม
    0.47
    Ⲗ
    0.46
    🐘
    0.45
     tartalmaz
    0.44
    していました
    0.43
    Ⲕ
    0.43
    канчи
    0.43
    鉾
    0.43
    ນະ
    0.42
    POSITIVE LOGITS
    j
    0.64
    ed
    0.49
    fabric
    0.46
    Fabric
    0.45
    ll
    0.44
    pp
    0.44
     Fabric
    0.43
    es
    0.43
    ce
    0.42
    lo
    0.42
    Act Density 0.002%

    No Known Activations