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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Generator
    -0.08
    locs
    -0.07
     ск
    -0.06
     Михай
    -0.06
    ्पर
    -0.06
    VICE
    -0.06
     Pis
    -0.06
     justify
    -0.06
    _Create
    -0.06
    AFF
    -0.06
    POSITIVE LOGITS
    loub
    0.07
    '],
↵
    0.07
     :|
    0.07
    بت
    0.07
     stylesheet
    0.07
    кол
    0.06
     \(
    0.06
    \">\
    0.06
    koli
    0.06
     demise
    0.06
    Act Density 0.016%

    No Known Activations