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

    Neuronpedia

    INDEX
    Explanations

    size, length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AREA
    -0.07
    收
    -0.07
     pers
    -0.07
     Nad
    -0.07
    _recall
    -0.07
    申请
    -0.06
    stead
    -0.06
    -upload
    -0.06
    lint
    -0.06
    check
    -0.06
    POSITIVE LOGITS
    pragma
    0.07
    (enc
    0.07
     lasers
    0.07
    ゔ
    0.07
    긔
    0.07
    ⼈
    0.07
    𝓱
    0.07
    価
    0.07
    //---------------------------------------------------------------------------↵↵
    0.07
    顆
    0.06
    Act Density 0.008%

    No Known Activations