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

    Neuronpedia

    INDEX
    Explanations

    free wave premium power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лган
    0.40
     Tomas
    0.39
    ERVER
    0.38
     تام
    0.38
    بانی
    0.38
     এসএম
    0.38
     Mosca
    0.37
     Rhino
    0.37
    ٹرول
    0.37
     PPC
    0.37
    POSITIVE LOGITS
    edd
    0.47
    Edd
    0.44
     eddy
    0.42
     оди
    0.41
     eddies
    0.41
    dt
    0.40
    odt
    0.40
    лау
    0.39
     اڈ
    0.39
     across
    0.38
    Act Density 0.000%

    No Known Activations