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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mata
    -0.07
    Define
    -0.07
     inviting
    -0.06
    Lee
    -0.06
    Thin
    -0.06
    IAM
    -0.06
    alarm
    -0.06
    eneg
    -0.06
     "*
    -0.06
    Star
    -0.06
    POSITIVE LOGITS
    測
    0.06
     synagogue
    0.06
    ераль
    0.06
    етель
    0.06
    scri
    0.06
     pll
    0.06
    LastError
    0.06
    漂
    0.06
     госп
    0.06
    (MediaType
    0.06
    Act Density 0.024%

    No Known Activations