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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrar
    -0.07
    -grand
    -0.07
    /main
    -0.07
     noses
    -0.07
     glucose
    -0.06
    _dynamic
    -0.06
    _MUT
    -0.06
     {}\
    -0.06
    -inline
    -0.06
     participating
    -0.06
    POSITIVE LOGITS
    arnings
    0.08
    atchet
    0.07
    ifton
    0.07
     Wheeler
    0.07
    geh
    0.07
    reek
    0.06
     Wolfgang
    0.06
     Auction
    0.06
     Church
    0.06
    itra
    0.06
    Act Density 0.018%

    No Known Activations