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

    Neuronpedia

    INDEX
    Explanations

    brand names / service prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.88
    dır
    0.86
    c
    0.86
    w
    0.75
    i
    0.74
    ي
    0.72
    ti
    0.71
    ta
    0.68
    ين
    0.68
    v
    0.67
    POSITIVE LOGITS
    4
    0.65
     Critics
    0.58
     médicos
    0.57
    5
    0.56
     musicals
    0.55
     Physicians
    0.55
    OV
    0.54
    ంగ్
    0.54
    桃
    0.53
    OVE
    0.52
    Act Density 0.351%

    No Known Activations