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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADE
    -0.08
    解
    -0.07
    .bunifu
    -0.07
    _pd
    -0.06
    ?:
    -0.06
    -ready
    -0.06
    .KeyPress
    -0.06
    _da
    -0.06
    タ
    -0.06
    のだ
    -0.06
    POSITIVE LOGITS
     duel
    0.07
    designation
    0.07
    ΕΧ
    0.06
     direccion
    0.06
    (frames
    0.06
    ('*
    0.06
     vzděl
    0.06
     seria
    0.06
    stroy
    0.06
     meme
    0.06
    Act Density 0.013%

    No Known Activations