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

    Neuronpedia

    INDEX
    Explanations

    rhythm and cadence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.39
    ä
    1.30
    se
    1.15
    end
    1.13
    ge
    1.13
    be
    1.09
    ite
    1.09
    1
    1.09
    ete
    1.08
    ene
    1.06
    POSITIVE LOGITS
    ور
    1.13
    bindingFields
    1.13
    و
    1.12
     Elke
    1.06
    ى
    1.06
    스를
    1.05
     Aguil
    1.05
     cinqui
    1.04
     Jezus
    1.02
    の設定
    1.01
    Act Density 0.007%

    No Known Activations