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

    Neuronpedia

    INDEX
    Explanations

    say "product"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lexer
    -0.07
    WSTR
    -0.07
    mişti
    -0.06
     getActivity
    -0.06
    What
    -0.06
     Twelve
    -0.06
     South
    -0.06
    ased
    -0.06
    =[
    -0.06
     Reaction
    -0.06
    POSITIVE LOGITS
    ฬ
    0.08
    LERİ
    0.07
     unins
    0.06
    บบ
    0.06
     notorious
    0.06
     constructed
    0.06
    ้เป
    0.06
    귀
    0.06
     accidentally
    0.06
    ..'
    0.06
    Act Density 0.079%

    No Known Activations