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

    Neuronpedia

    INDEX
    Explanations

    dolor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uno
    -0.08
    -earth
    -0.07
    Nd
    -0.07
    ឍ
    -0.07
    -bit
    -0.07
     activation
    -0.07
     grasp
    -0.07
    /auto
    -0.07
    待ち
    -0.07
     Nä
    -0.07
    POSITIVE LOGITS
     FormControl
    0.08
    GridColumn
    0.07
     الهيئة
    0.07
     Posting
    0.07
    cess
    0.06
    争论
    0.06
    🚩
    0.06
    における
    0.06
    给她
    0.06
     hoping
    0.06
    Act Density 0.007%

    No Known Activations