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

    Neuronpedia

    INDEX
    Explanations

    gaining something that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হল
    0.49
    γου
    0.44
    fac
    0.41
     stalks
    0.41
    ewalk
    0.41
    boden
    0.41
    is
    0.40
    bdb
    0.39
    OfDeath
    0.39
     eZ
    0.39
    POSITIVE LOGITS
     movimientos
    0.52
     konkur
    0.49
     пишет
    0.48
    Desde
    0.48
     SUMMARY
    0.47
    .:
    0.46
    成就
    0.46
     патри
    0.46
     движения
    0.45
    舆
    0.45
    Act Density 0.000%

    No Known Activations