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

    Neuronpedia

    INDEX
    Explanations

    morphology and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    4.38
    ف
    4.21
    فري
    3.14
    an
    3.08
    า
    3.05
    y
    2.85
    לע
    2.85
    علم
    2.77
    ので
    2.68
    z
    2.64
    POSITIVE LOGITS
    ńca
    3.09
     Él
    2.88
     dessen
    2.67
    全年
    2.63
    2.46
    2.46
    ل
    2.46
    cmds
    2.45
    𝒐
    2.44
    С
    2.43
    Act Density 0.035%

    No Known Activations