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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monot
    -0.07
     academic
    -0.07
     baseball
    -0.06
     Concrete
    -0.06
    calendar
    -0.06
     přiroz
    -0.06
     weather
    -0.06
    _bh
    -0.06
    やって
    -0.06
     whistle
    -0.06
    POSITIVE LOGITS
     �
    0.08
    _GL
    0.07
    اى
    0.07
     влас
    0.06
     �
    0.06
    AMPL
    0.06
    .FromSeconds
    0.06
     Ř
    0.06
    *******
↵
    0.06
    gii
    0.06
    Act Density 0.054%

    No Known Activations