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

    Neuronpedia

    INDEX
    Explanations

    Because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fargo
    0.52
     дел
    0.48
    dominant
    0.45
     Edwards
    0.44
    corper
    0.43
    dominal
    0.43
    би
    0.42
     oppressive
    0.40
     suốt
    0.40
    नेल
    0.40
    POSITIVE LOGITS
     jit
    0.44
     waiters
    0.42
    ⇵
    0.42
    FBSDKSettings
    0.41
     woes
    0.41
    ServiceName
    0.40
     አይደለም
    0.40
    StaticHandler
    0.39
     সন্ন
    0.39
     toiletries
    0.39
    Act Density 0.003%

    No Known Activations