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

    Neuronpedia

    INDEX
    Explanations

    say "ch" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pry
    -0.07
     arrested
    -0.06
     Depending
    -0.06
    لاین
    -0.06
     unve
    -0.06
    _feed
    -0.06
    ์ม
    -0.06
    itates
    -0.06
    pillar
    -0.06
    charts
    -0.06
    POSITIVE LOGITS
     东
    0.07
     خدا
    0.07
    _bind
    0.07
    日の
    0.07
     BEN
    0.06
     />}
    0.06
     corrid
    0.06
    (日
    0.06
    elsing
    0.06
    RAIN
    0.06
    Act Density 0.001%

    No Known Activations