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

    Neuronpedia

    INDEX
    Explanations

    scientific identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }}>↵
    -0.07
    Uni
    -0.07
     scenarios
    -0.07
    sep
    -0.07
    etsk
    -0.07
     outcome
    -0.07
     scenario
    -0.06
     DEL
    -0.06
     womb
    -0.06
    hod
    -0.06
    POSITIVE LOGITS
    erializer
    0.07
    INIT
    0.07
    ircon
    0.06
    طع
    0.06
    (loss
    0.06
     Тур
    0.06
     워
    0.06
    gew
    0.06
     Iterable
    0.06
     Trek
    0.06
    Act Density 0.240%

    No Known Activations