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

    Neuronpedia

    INDEX
    Explanations

    casinos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یشن
    0.50
    skar
    0.49
    ौल
    0.48
    ುತ್ತವೆ
    0.47
    <0x86>
    0.46
     Kershaw
    0.46
    ání
    0.46
    iciable
    0.46
     skirm
    0.45
     Стаўкі
    0.45
    POSITIVE LOGITS
    u
    0.61
    ла
    0.60
    -
    0.57
    ล
    0.54
    ↵↵
    0.54
    ur
    0.51
    w
    0.51
     minha
    0.51
    7
    0.49
    8
    0.49
    Act Density 0.000%

    No Known Activations