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

    Neuronpedia

    INDEX
    Explanations

    Reliance and Trinidad Tobago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.68
    ă
    0.65
    ่
    0.63
    هاي
    0.61
    ု
    0.56
    ني
    0.54
    ё
    0.54
    CAT
    0.54
    ότερα
    0.54
    這
    0.54
    POSITIVE LOGITS
     옷
    0.57
     השי
    0.54
     حدی
    0.52
     amplifier
    0.52
     হেঁটে
    0.52
     생각해
    0.52
     thoughts
    0.51
     wody
    0.51
     หมาย
    0.51
     Disposition
    0.51
    Act Density 0.000%

    No Known Activations