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

    Neuronpedia

    INDEX
    Explanations

    clarification and proliferation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穀
    0.41
     covalently
    0.39
    カラ
    0.38
    plr
    0.38
     ta
    0.36
     goods
    0.35
     FUNCTION
    0.35
     chrom
    0.34
     قلنا
    0.34
     Kabhi
    0.34
    POSITIVE LOGITS
    ثمار
    0.45
    народ
    0.41
    FAST
    0.40
     بناء
    0.40
    >>)
    0.39
    )((
    0.37
     proliferate
    0.37
    Twitter
    0.37
    лната
    0.37
    Diploma
    0.37
    Act Density 0.000%

    No Known Activations