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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ensuing
    0.64
     northward
    0.63
    प्रीत
    0.59
     ಸಂಗೀತ
    0.58
     respectful
    0.57
    cursion
    0.57
    сат
    0.57
     dakkh
    0.56
     userAnswer
    0.56
    usta
    0.55
    POSITIVE LOGITS
    搵
    0.73
    앱
    0.63
     configs
    0.61
     blobs
    0.61
     herpes
    0.61
    锈
    0.60
     முடிய
    0.57
    হর
    0.57
     monolith
    0.57
     apps
    0.57
    Act Density 0.000%

    No Known Activations