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

    Neuronpedia

    INDEX
    Explanations

    budget ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anders
    0.39
    перь
    0.39
     verdict
    0.37
     Fisheries
    0.37
    じゃない
    0.35
    \}$.
    0.35
    ("#{
    0.35
    ('/')
    0.34
     دام
    0.34
     Verdict
    0.34
    POSITIVE LOGITS
    ició
    0.41
    ską
    0.40
    ায়ী
    0.39
     tendencia
    0.39
    ția
    0.39
    posted
    0.39
    chocolate
    0.39
    اية
    0.39
    chaos
    0.38
    jetty
    0.38
    Act Density 0.000%

    No Known Activations