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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     президент
    -0.07
    .epoch
    -0.07
     majors
    -0.07
    (cookie
    -0.06
     deck
    -0.06
    them
    -0.06
    "]').
    -0.06
     хот
    -0.06
    =all
    -0.06
    startup
    -0.06
    POSITIVE LOGITS
    ticks
    0.07
    土
    0.06
     SDL
    0.06
     Sources
    0.06
     gradual
    0.06
     прид
    0.06
    ERN
    0.06
    DUCTION
    0.06
    rating
    0.06
    sgi
    0.06
    Act Density 0.023%

    No Known Activations