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

    Neuronpedia

    INDEX
    Explanations

    food dishes desserts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ِی
    0.86
     sanguine
    0.86
     prophylactic
    0.84
    (
    0.84
     که
    0.80
     stoichiometry
    0.80
     prophylaxis
    0.79
     hospitalized
    0.79
    زی
    0.78
     bibliographic
    0.78
    POSITIVE LOGITS
    at
    1.23
    n
    0.98
    NUMBER
    0.91
     言っ
    0.91
     ansch
    0.88
     Anwendung
    0.85
     elenco
    0.85
     Actualmente
    0.85
     ideale
    0.85
     pudi
    0.84
    Act Density 0.002%

    No Known Activations