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

    Neuronpedia

    INDEX
    Explanations

    arraycopy or insurance amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ває
    0.74
    ປ
    0.73
    nosti
    0.71
     COUNT
    0.71
    واره
    0.69
     Err
    0.68
     IllegalArgument
    0.68
     indisc
    0.68
     faiblement
    0.68
     Variance
    0.68
    POSITIVE LOGITS
    än
    0.98
    एन
    0.93
    ر
    0.84
    नी
    0.79
    ون
    0.79
     sobbing
    0.78
     οποίος
    0.77
     father
    0.75
    ட்கள்
    0.75
    ud
    0.74
    Act Density 0.000%

    No Known Activations