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

    Neuronpedia

    INDEX
    Explanations

    hit or miss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.55
    ",
    0.54
    "
    0.50
    IAN
    0.50
    l
    0.50
    \
    0.48
    _
    0.48
    Misc
    0.47
    ires
    0.46
    Marg
    0.46
    POSITIVE LOGITS
    anjana
    0.57
    aların
    0.56
     በሽታ
    0.54
    HTTPSampler
    0.54
     Gł
    0.54
     grave
    0.53
     glucose
    0.53
     وړاندوینې
    0.52
    ονται
    0.52
     नाइट्रेट
    0.52
    Act Density 0.000%

    No Known Activations