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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heu
    0.40
    দ্ম
    0.37
     nef
    0.36
     gevo
    0.36
     perox
    0.36
    leck
    0.35
    chwitz
    0.34
    icel
    0.34
     വള
    0.34
     >>=
    0.34
    POSITIVE LOGITS
     list
    1.70
     bullet
    1.65
     bullets
    1.51
     lists
    1.47
     목록
    1.45
     Bullet
    1.41
    list
    1.41
    Bullet
    1.39
     список
    1.39
    bullet
    1.35
    Act Density 0.062%

    No Known Activations