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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shoulder
    -0.07
    athing
    -0.07
    γή
    -0.07
    Datum
    -0.07
    وتر
    -0.07
    InlineData
    -0.06
     Buffalo
    -0.06
     vape
    -0.06
    [E
    -0.06
    dere
    -0.06
    POSITIVE LOGITS
    งเศ
    0.07
    ).^
    0.06
    ्पत
    0.06
     cn
    0.06
    ammable
    0.06
     Hof
    0.06
     Pelosi
    0.06
    (set
    0.06
    chars
    0.06
    КО
    0.05
    Act Density 0.024%

    No Known Activations