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

    Neuronpedia

    INDEX
    Explanations

    RDD Collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ATTR
    -0.06
    /q
    -0.06
    Pressure
    -0.06
    SpecWarn
    -0.06
    Attr
    -0.06
     نامه
    -0.06
     zpět
    -0.06
    SetValue
    -0.06
    써
    -0.06
    (b
    -0.06
    POSITIVE LOGITS
     Bs
    0.07
    TeX
    0.07
     minors
    0.07
     invert
    0.06
     ConcurrentHashMap
    0.06
    lady
    0.06
    iffe
    0.06
    nung
    0.06
    ажд
    0.06
     sixty
    0.06
    Act Density 0.003%

    No Known Activations