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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     showDialog
    -0.07
     caliente
    -0.07
     FileInputStream
    -0.07
     режим
    -0.07
     focuses
    -0.07
     är
    -0.07
    אחראי
    -0.07
     הסרט
    -0.07
    archives
    -0.06
    ipsoid
    -0.06
    POSITIVE LOGITS
     cellul
    0.07
     donation
    0.07
    屡
    0.07
     lar
    0.07
    蟹
    0.07
    给她
    0.07
    PHONE
    0.07
    啥
    0.07
    荫
    0.06
     ℝ
    0.06
    Act Density 0.038%

    No Known Activations