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

    Neuronpedia

    INDEX
    Explanations

    handling errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Austin
    0.84
     Revenues
    0.81
     Charges
    0.80
     Diversity
    0.80
     anticor
    0.79
     ETFs
    0.78
     Consiglio
    0.78
     Anal
    0.76
     Brokers
    0.76
     considering
    0.76
    POSITIVE LOGITS
    𝗅
    0.82
    üş
    0.79
     сфере
    0.73
     என்கிற
    0.73
     рэгістра
    0.73
    üst
    0.72
    üşt
    0.72
    щены
    0.72
    лены
    0.71
     своей
    0.71
    Act Density 0.002%

    No Known Activations