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

    Neuronpedia

    INDEX
    Explanations

    reflecting on the past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .utc
    -0.06
     pi
    -0.06
    欧美
    -0.06
    ordinal
    -0.06
     العالم
    -0.06
     standart
    -0.06
    _receive
    -0.06
     N
    -0.06
    /npm
    -0.06
     weighted
    -0.06
    POSITIVE LOGITS
    .Ab
    0.07
     pict
    0.07
     biting
    0.07
     fragment
    0.06
    paragus
    0.06
     pageInfo
    0.06
    RIPTION
    0.06
    رف
    0.06
    днання
    0.06
     inventory
    0.06
    Act Density 0.088%

    No Known Activations