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

    Neuronpedia

    INDEX
    Explanations

    evening, bedtime, scams, debt, programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uos
    0.39
    F
    0.37
     উদ্দীপ
    0.36
     Total
    0.35
     ActiveX
    0.35
     Specific
    0.34
    FAR
    0.34
     மனித
    0.33
    FP
    0.33
    ін
    0.33
    POSITIVE LOGITS
     ähm
    0.46
    hhhhhhhh
    0.42
    bracelet
    0.41
    ছাড়া
    0.40
     Mikh
    0.39
    harris
    0.39
    ちょっと
    0.39
    𝒞
    0.39
    okay
    0.38
    hhhh
    0.38
    Act Density 0.000%

    No Known Activations