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

    Neuronpedia

    INDEX
    Explanations

    to step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     стрем
    0.50
    inspiring
    0.48
    ösungen
    0.48
    ▟
    0.46
    ulsion
    0.46
    supporting
    0.45
    arów
    0.44
    abileceğ
    0.44
    ceived
    0.44
    lgan
    0.44
    POSITIVE LOGITS
     casa
    0.46
     paid
    0.44
    BE
    0.42
     estamos
    0.42
    θη
    0.41
    TGF
    0.40
    (
    0.40
     preferred
    0.40
    7
    0.38
    α
    0.37
    Act Density 0.000%

    No Known Activations