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

    Neuronpedia

    INDEX
    Explanations

    freedom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Finish
    -0.07
     todd
    -0.06
    _SELF
    -0.06
    rocket
    -0.06
     Hentai
    -0.06
    woo
    -0.06
     zenith
    -0.06
    _LAST
    -0.06
    paint
    -0.06
     priority
    -0.06
    POSITIVE LOGITS
    ivities
    0.08
    рогра
    0.06
    ruit
    0.06
    ِر
    0.06
     licensing
    0.06
    _amt
    0.06
     /↵
    0.06
     Blackjack
    0.06
    VT
    0.06
    .Ct
    0.06
    Act Density 0.014%

    No Known Activations