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

    Neuronpedia

    INDEX
    Explanations

    female pronouns and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    页面存档备份
    0.43
    䐍
    0.42
    өт
    0.38
    വുമായി
    0.36
     Polaribacter
    0.36
    兩個
    0.36
    阃
    0.36
    zechoslovak
    0.36
     PROBLEMS
    0.36
     Fractals
    0.36
    POSITIVE LOGITS
    Mr
    0.46
    mr
    0.44
     Ms
    0.42
    Ms
    0.42
     mr
    0.41
     ông
    0.40
    0.40
     der
    0.39
    MR
    0.38
     então
    0.38
    Act Density 0.001%

    No Known Activations