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

    Neuronpedia

    INDEX
    Explanations

    quotations and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vehicle
    -0.07
    ugo
    -0.07
     Dow
    -0.07
    on
    -0.07
     material
    -0.06
     attracting
    -0.06
    olio
    -0.06
    lane
    -0.06
    /AFP
    -0.06
    アニメ
    -0.06
    POSITIVE LOGITS
     этот
    0.07
    elerik
    0.06
     recognize
    0.06
    innacle
    0.06
     Till
    0.06
    KeySpec
    0.06
     wsz
    0.05
     Christina
    0.05
     фин
    0.05
     همچ
    0.05
    Act Density 0.103%

    No Known Activations