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

    Neuronpedia

    INDEX
    Explanations

    Her

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mor
    0.48
    mor
    0.45
     أم
    0.43
     Mor
    0.41
     žiad
    0.38
    Mor
    0.37
     exemplary
    0.37
    eret
    0.36
    itere
    0.36
    itaire
    0.36
    POSITIVE LOGITS
     Towns
    0.42
    "%>
    0.38
     towns
    0.36
    polis
    0.36
    instrList
    0.36
     գ
    0.36
    Supported
    0.35
     Gorgeous
    0.35
    팝
    0.35
    สรร
    0.35
    Act Density 0.000%

    No Known Activations