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

    Neuronpedia

    INDEX
    Explanations

    categorized text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dT
    0.43
    Ajax
    0.41
    Trendy
    0.40
    替换
    0.40
    drinks
    0.39
    ಮಾರ
    0.39
    Confidence
    0.38
    شنامه
    0.37
     CGRect
    0.37
    人不
    0.37
    POSITIVE LOGITS
     diligent
    0.38
    תן
    0.38
    ocrite
    0.38
     കരാ
    0.38
     dichos
    0.37
     prodigious
    0.37
     telemedicine
    0.36
     Sebasti
    0.36
     interprets
    0.36
     dichas
    0.36
    Act Density 0.000%

    No Known Activations