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

    Neuronpedia

    INDEX
    Explanations

    fines and penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     საჭ
    0.54
    稃
    0.47
     ஆரோக்கிய
    0.47
     అనేది
    0.46
     എന്നത്
    0.45
     χα
    0.45
     NuGet
    0.45
     Gesundheit
    0.45
     nécess
    0.44
     প্রশ্নোত্তর
    0.44
    POSITIVE LOGITS
    重大
    0.46
    Payroll
    0.45
    HR
    0.45
    gb
    0.44
    GB
    0.43
    ISO
    0.42
    MB
    0.41
     penalty
    0.41
     damning
    0.41
    5
    0.40
    Act Density 0.002%

    No Known Activations