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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pages
    -0.07
     Cher
    -0.07
     viruses
    -0.07
     lecturer
    -0.06
     economical
    -0.06
     regulation
    -0.06
     Ek
    -0.06
     Wish
    -0.06
     oby
    -0.06
    _CANCEL
    -0.06
    POSITIVE LOGITS
    wrap
    0.07
    habit
    0.06
     indexes
    0.06
    pmat
    0.06
    elsius
    0.06
    lsruhe
    0.06
    erland
    0.06
     thankful
    0.06
    áky
    0.06
     diminish
    0.06
    Act Density 0.052%

    No Known Activations