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

    Neuronpedia

    INDEX
    Explanations

    optera

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posters
    -0.07
    jandro
    -0.07
     Bent
    -0.07
    rint
    -0.07
    -negative
    -0.07
     resurrect
    -0.06
     Harrison
    -0.06
    Black
    -0.06
     Man
    -0.06
    utt
    -0.06
    POSITIVE LOGITS
     виступ
    0.07
    :UIControlEvent
    0.06
    (火
    0.06
    ORIZED
    0.06
    дел
    0.06
    roti
    0.06
     응
    0.06
     interven
    0.06
     вплив
    0.06
     chiếc
    0.06
    Act Density 0.001%

    No Known Activations