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

    Neuronpedia

    INDEX
    Explanations

    drawing code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debounce
    -0.06
     нічого
    -0.06
     Oval
    -0.06
     有
    -0.06
    ��
    -0.06
    に向
    -0.06
    .progressBar
    -0.06
    альне
    -0.06
     взаєм
    -0.06
     henüz
    -0.06
    POSITIVE LOGITS
    Types
    0.08
     secretion
    0.07
     literary
    0.07
     Desc
    0.07
     historian
    0.06
     struggle
    0.06
     tweaked
    0.06
     Public
    0.06
     makes
    0.06
    Egypt
    0.06
    Act Density 0.006%

    No Known Activations