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

    Neuronpedia

    INDEX
    Explanations

    FAQ section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    achlor
    0.41
    लेंट
    0.41
    éria
    0.40
    Ֆ
    0.39
     subsequently
    0.38
    ій
    0.38
    æk
    0.38
    alanine
    0.38
    ácia
    0.38
    ända
    0.38
    POSITIVE LOGITS
     assegn
    0.44
     voluptates
    0.44
     имуще
    0.44
     viaj
    0.43
     requisition
    0.42
     intercamb
    0.42
    に近い
    0.42
    踹
    0.42
     genitori
    0.41
     Swamp
    0.41
    Act Density 0.000%

    No Known Activations