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

    Neuronpedia

    INDEX
    Explanations

    Special characters/delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ained
    -0.07
    اص
    -0.07
    插
    -0.06
    חשבו
    -0.06
    佩
    -0.06
    ается
    -0.06
     ;
↵
    -0.06
    ified
    -0.06
    _temp
    -0.06
    ملابس
    -0.06
    POSITIVE LOGITS
    javax
    0.07
     javax
    0.07
     UIViewController
    0.07
    .tree
    0.07
     actionBar
    0.07
    :hover
    0.07
    .onCreate
    0.07
    ること
    0.07
    EPHIR
    0.07
    룄
    0.06
    Act Density 0.007%

    No Known Activations