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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jus
    -0.08
     It
    -0.07
    It
    -0.07
    يث
    -0.07
    ivirus
    -0.07
    hapus
    -0.06
     GetById
    -0.06
     detective
    -0.06
     fifth
    -0.06
    ("{
    -0.06
    POSITIVE LOGITS
     are
    0.15
     Are
    0.11
     ARE
    0.11
    Are
    0.10
     were
    0.10
     aren
    0.10
     são
    0.09
    _are
    0.09
    —are
    0.08
     Aren
    0.08
    Act Density 0.432%

    No Known Activations