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

    Neuronpedia

    INDEX
    Explanations

    Foreign articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dif
    -0.07
     mist
    -0.07
    (buf
    -0.06
     Hem
    -0.06
     In
    -0.06
     Met
    -0.06
     postId
    -0.06
    .In
    -0.06
     masturb
    -0.06
    std
    -0.06
    POSITIVE LOGITS
    \",\"
    0.06
     zprávy
    0.06
    .the
    0.06
     vàng
    0.06
     yummy
    0.06
    äge
    0.06
    گان
    0.06
     коп
    0.06
    тор
    0.06
     серьез
    0.06
    Act Density 0.023%

    No Known Activations