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

    Neuronpedia

    INDEX
    Explanations

    webpack configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hydraz
    1.30
    ی
    1.20
    ^{*}(
    1.20
    owali
    1.20
    bounds
    1.19
    Время
    1.17
    qos
    1.16
    ිබ
    1.14
    caf
    1.13
     emojis
    1.13
    POSITIVE LOGITS
     ח
    1.16
     ¿
    0.94
    ような
    0.94
    しっかり
    0.93
     المست
    0.88
    設け
    0.88
    pped
    0.86
     النار
    0.86
    ين
    0.84
     стен
    0.83
    Act Density 0.000%

    No Known Activations