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

    Neuronpedia

    INDEX
    Explanations

    file paths/directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rones
    -0.06
    erves
    -0.06
     sürec
    -0.06
    rollable
    -0.06
    partial
    -0.06
     op
    -0.06
    bbc
    -0.06
     мл
    -0.06
    493
    -0.06
     Sb
    -0.06
    POSITIVE LOGITS
     confirmPassword
    0.07
     miêu
    0.07
    .getPassword
    0.07
     Tobacco
    0.07
     redirectTo
    0.06
    myp
    0.06
     Gather
    0.06
    .shared
    0.06
     October
    0.06
    ~↵↵
    0.06
    Act Density 0.012%

    No Known Activations