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

    Neuronpedia

    INDEX
    Explanations

    sameness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ILLISECONDS
    -0.07
    ол
    -0.06
     Holly
    -0.06
    ६
    -0.06
    home
    -0.06
    談
    -0.06
     Bur
    -0.06
     три
    -0.06
    meni
    -0.06
     Tol
    -0.06
    POSITIVE LOGITS
    ELL
    0.07
    čku
    0.07
    Preparing
    0.07
    _IMAGES
    0.07
    _waiting
    0.07
    (sequence
    0.06
    uggling
    0.06
    lew
    0.06
    ewhat
    0.06
    CLUDING
    0.06
    Act Density 0.013%

    No Known Activations