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
     lil
    -0.08
    支援
    -0.07
     שח
    -0.07
     interruption
    -0.07
     distracted
    -0.07
     ..."↵↵
    -0.07
     Elle
    -0.07
     Pey
    -0.07
     portal
    -0.07
     modification
    -0.07
    POSITIVE LOGITS
    _BOX
    0.08
    чен
    0.07
    รณ
    0.07
    🏙
    0.07
    Ǐ
    0.07
    ->[
    0.07
    ढ
    0.07
    呼声
    0.07
    ดาร
    0.06
    =en
    0.06
    Act Density 0.004%

    No Known Activations