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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    程
    -0.08
    Ρ
    -0.07
     GENER
    -0.06
    aes
    -0.06
    čky
    -0.06
    Wars
    -0.06
     unfortunate
    -0.06
    WithEmailAndPassword
    -0.06
    ान
    -0.06
    孩子
    -0.06
    POSITIVE LOGITS
    xffffffff
    0.07
    ль
    0.07
    /categories
    0.07
     мл
    0.07
    !!!
    0.06
     revolt
    0.06
     exhibit
    0.06
    립니다
    0.06
    (fb
    0.06
    進行
    0.06
    Act Density 0.009%

    No Known Activations