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

    Neuronpedia

    INDEX
    Explanations

    Personal narratives and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DVR
    -0.07
     "=
    -0.07
     нар
    -0.06
     jiných
    -0.06
     Tel
    -0.06
    _UClass
    -0.06
     реп
    -0.06
    (clock
    -0.06
    _MY
    -0.06
     tarihli
    -0.06
    POSITIVE LOGITS
     convince
    0.07
    ervatives
    0.07
    gli
    0.06
    -Series
    0.06
     excluding
    0.06
    ом
    0.06
    се
    0.06
     Argument
    0.06
    ifferential
    0.06
     dominate
    0.06
    Act Density 0.001%

    No Known Activations