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

    Neuronpedia

    INDEX
    Explanations

    called

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     farmhouse
    -0.07
    ervo
    -0.07
     getopt
    -0.06
     seeming
    -0.06
     southwestern
    -0.06
     deco
    -0.06
    .Rule
    -0.06
    upd
    -0.06
     postup
    -0.06
    (mutex
    -0.06
    POSITIVE LOGITS
     stip
    0.07
    αρά
    0.06
    heard
    0.06
    /authentication
    0.06
    P
    0.06
    .white
    0.06
    ipment
    0.06
    ***↵↵
    0.06
    antor
    0.06
    ;'↵
    0.06
    Act Density 0.019%

    No Known Activations