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

    Neuronpedia

    INDEX
    Explanations

    Clojure code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    0.59
    ଣ୍
    0.53
    R
    0.52
     başlay
    0.48
    G
    0.48
    oad
    0.47
    K
    0.47
    startTime
    0.46
    aphthalene
    0.46
     võivad
    0.45
    POSITIVE LOGITS
     Bots
    0.55
     tanaman
    0.45
     quân
    0.44
     salari
    0.43
     transaction
    0.42
     Research
    0.42
     identidad
    0.42
     physic
    0.42
     payment
    0.42
     همچنین
    0.42
    Act Density 0.008%

    No Known Activations