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

    Neuronpedia

    INDEX
    Explanations

    foreign scripts and html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     líder
    0.43
     alá
    0.40
     ADB
    0.39
     útil
    0.39
     zee
    0.38
     ON
    0.37
     voz
    0.37
     phòng
    0.37
     allá
    0.37
     bây
    0.37
    POSITIVE LOGITS
    <h3>
    0.45
    დას
    0.40
    gr
    0.39
    陰
    0.39
    aura
    0.38
    ഐ
    0.38
    amplitude
    0.37
     ಆರ್
    0.37
    ഡി
    0.36
    utilise
    0.36
    Act Density 0.000%

    No Known Activations