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

    Neuronpedia

    INDEX
    Explanations

    gender, languages, policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kiyor
    0.43
    قاف
    0.41
     achievement
    0.40
    یثیت
    0.40
    MVCProject
    0.40
    béco
    0.39
     genealogical
    0.39
     وحتى
    0.39
    حدث
    0.38
    ']))->
    0.38
    POSITIVE LOGITS
    rg
    0.41
    ir
    0.40
    RR
    0.39
    ri
    0.39
    RY
    0.38
    RG
    0.38
     =
    0.37
    ilación
    0.36
    ring
    0.36
    Figures
    0.36
    Act Density 0.090%

    No Known Activations