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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ej
    -0.06
     apologise
    -0.06
     bush
    -0.06
    μπο
    -0.06
     dne
    -0.06
    cooldown
    -0.06
     Davis
    -0.06
     Calvin
    -0.06
    Davis
    -0.06
    mith
    -0.06
    POSITIVE LOGITS
    TARGET
    0.07
     beurette
    0.06
    รรม
    0.06
     마
    0.06
     "'"
    0.06
    اسی
    0.06
    Styles
    0.06
     Moms
    0.06
     heure
    0.06
     ziyaret
    0.06
    Act Density 0.005%

    No Known Activations