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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     generations
    -0.07
     haired
    -0.07
     علیه
    -0.06
     povin
    -0.06
     adore
    -0.06
    .doc
    -0.06
    cccc
    -0.06
    ationToken
    -0.06
     něk
    -0.06
    kest
    -0.06
    POSITIVE LOGITS
    IMAGE
    0.06
    prehensive
    0.06
     Augusta
    0.06
    ilitation
    0.06
     failure
    0.06
     Fiji
    0.06
    ),↵↵
    0.06
    -inch
    0.06
    asbourg
    0.06
     Kab
    0.06
    Act Density 0.005%

    No Known Activations