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

    Neuronpedia

    INDEX
    Explanations

    sentencing disparities and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.98
    ة
    0.75
     sentence
    0.74
    ने
    0.72
    ال
    0.68
    ="
    0.67
     managerial
    0.65
     stretcher
    0.65
    ästä
    0.64
     resonance
    0.63
    POSITIVE LOGITS
    ↵↵
    0.86
    are
    0.83
    to
    0.79
    ave
    0.73
     Assessing
    0.72
    ।
    0.72
    त्ती
    0.69
     Redist
    0.69
     தெரிவித்த
    0.66
    toa
    0.65
    Act Density 0.000%

    No Known Activations