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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istica
    -0.07
     sciences
    -0.07
    576
    -0.06
     quella
    -0.06
     tragic
    -0.06
    zier
    -0.06
     Tuesday
    -0.06
     اختلاف
    -0.06
    .ms
    -0.06
    ector
    -0.06
    POSITIVE LOGITS
     [...]↵↵
    0.07
     Sydney
    0.06
    Stretch
    0.06
    (close
    0.06
    _make
    0.06
    _COUNTRY
    0.06
    คราม
    0.06
     Burr
    0.06
     Cavs
    0.06
     }}"></
    0.06
    Act Density 0.037%

    No Known Activations