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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٥
    -0.06
    ieee
    -0.06
    iggers
    -0.06
     bureau
    -0.06
    �
    -0.06
    .dtp
    -0.06
    ेखत
    -0.06
    ism
    -0.06
     Jing
    -0.06
     rd
    -0.06
    POSITIVE LOGITS
    SKU
    0.07
    .flatten
    0.07
    .likes
    0.07
    Важ
    0.06
     luckily
    0.06
    č
    0.06
    Ctrls
    0.06
    _values
    0.06
     través
    0.06
    Fax
    0.06
    Act Density 0.122%

    No Known Activations