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

    Neuronpedia

    INDEX
    Explanations

    Zenith ST, multiples of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     earning
    0.43
     California
    0.43
     Turkey
    0.40
    Acer
    0.40
     `"
    0.40
     Grant
    0.39
     Cardiology
    0.39
     hardening
    0.39
     Mackenzie
    0.39
     ഇനി
    0.39
    POSITIVE LOGITS
    쿠
    0.40
    LOOP
    0.38
    疖
    0.38
    클
    0.37
    ాన్ని
    0.37
     مي
    0.37
    نوات
    0.36
    云
    0.36
     reinst
    0.36
    મિક
    0.36
    Act Density 0.004%

    No Known Activations