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

    Neuronpedia

    INDEX
    Explanations

    it turns out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Email
    0.74
    Eye
    0.70
    Chat
    0.69
    Head
    0.60
    Payload
    0.60
    Badge
    0.60
    Ext
    0.59
    Effect
    0.59
    Пре
    0.57
    Lag
    0.57
    POSITIVE LOGITS
    า
    0.94
    u
    0.84
    ਾ
    0.75
     który
    0.71
    ி
    0.69
    ุ
    0.67
    ं
    0.66
    های
    0.63
    ный
    0.63
     orientado
    0.62
    Act Density 0.001%

    No Known Activations