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

    Neuronpedia

    INDEX
    Explanations

    FDIC insured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aid
    1.00
    ee
    0.91
    iye
    0.86
    ių
    0.85
    am
    0.84
    aire
    0.84
    up
    0.83
    ми
    0.82
    ae
    0.81
    underset
    0.81
    POSITIVE LOGITS
    ⅽ
    0.79
    苒
    0.76
     explor
    0.73
    いわ
    0.73
    ماً
    0.72
     Após
    0.71
     iza
    0.71
     サ
    0.71
     hermano
    0.70
     absoluto
    0.69
    Act Density 0.001%

    No Known Activations