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

    Neuronpedia

    INDEX
    Explanations

    conductor and current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.75
     align
    0.62
    g
    0.60
     aligned
    0.57
    h
    0.57
     kuid
    0.56
    С
    0.56
     OSError
    0.55
    Album
    0.53
     EMS
    0.53
    POSITIVE LOGITS
    ure
    0.64
    埶
    0.56
    wat
    0.52
    wra
    0.51
    oure
    0.51
     مِن
    0.50
     Kijk
    0.49
     يو
    0.49
    of
    0.49
     Тру
    0.48
    Act Density 0.000%

    No Known Activations