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

    Neuronpedia

    INDEX
    Explanations

    requesting assistance or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ν
    1.30
     Jenis
    1.22
    岖
    1.19
     рома
    1.16
    هَا
    1.16
    峋
    1.15
    Д
    1.14
    狨
    1.14
    hoch
    1.13
    ]++;
    1.12
    POSITIVE LOGITS
     defray
    1.42
     đỡ
    1.30
    ం
    1.27
     ích
    1.21
    о
    1.18
    ै
    1.18
     ويكيپيديا
    1.11
    is
    1.10
    ून
    1.09
    ot
    1.06
    Act Density 0.081%

    No Known Activations