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

    Neuronpedia

    INDEX
    Explanations

    conversion to radians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.76
    ay
    0.75
    ik
    0.74
     mwaka
    0.74
    ij
    0.73
    riya
    0.71
    ı
    0.70
     ඔවුන්
    0.70
    ១
    0.68
    uk
    0.68
    POSITIVE LOGITS
    a
    0.98
    ه
    0.91
    )
    0.87
    <0x93>
    0.81
    }
    0.79
    ↵
    0.76
    <0x94>
    0.72
    ה
    0.72
     Tragedy
    0.67
     Inquisition
    0.65
    Act Density 0.005%

    No Known Activations