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

    Neuronpedia

    INDEX
    Explanations

    sold out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sono
    0.79
     resum
    0.75
     negative
    0.74
    negative
    0.73
     excessive
    0.73
     টেলিভিশ
    0.73
    राइड
    0.70
    vascular
    0.70
     grossly
    0.70
     sain
    0.69
    POSITIVE LOGITS
    ering
    1.09
    eringen
    0.96
    ier
    0.91
    adura
    0.87
    atelli
    0.84
    adores
    0.76
    elti
    0.76
     ചേർ
    0.73
    adora
    0.72
    ERING
    0.71
    Act Density 0.006%

    No Known Activations