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

    Neuronpedia

    INDEX
    Explanations

    zerodha, zeroshot, zeromancer, zerodium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pp
    0.40
    󠁴
    0.38
     ravi
    0.36
    貥
    0.36
    िजन
    0.35
     sitting
    0.35
    接口
    0.34
     ભર
    0.34
    graph
    0.34
     scholars
    0.34
    POSITIVE LOGITS
    Tier
    0.45
     Tier
    0.42
    কন
    0.41
    Zer
    0.41
    زر
    0.40
    umlah
    0.38
    outi
    0.38
    rough
    0.37
     Zer
    0.37
    focusable
    0.37
    Act Density 0.004%

    No Known Activations