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

    Neuronpedia

    INDEX
    Explanations

    diverse/mixed topics and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ({_
    -0.07
    etxt
    -0.07
     frontier
    -0.06
    Colon
    -0.06
     programmes
    -0.06
     satellite
    -0.06
     ولكن
    -0.06
     outcomes
    -0.06
     homicide
    -0.06
    -mon
    -0.06
    POSITIVE LOGITS
     goalkeeper
    0.07
    livě
    0.07
     Buster
    0.06
    레
    0.06
     lurking
    0.06
    PER
    0.06
     первый
    0.06
     Final
    0.06
    oned
    0.06
     ViewPager
    0.06
    Act Density 0.000%

    No Known Activations