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

    Neuronpedia

    INDEX
    Explanations

    prepositions and possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     –
    -0.07
     Hand
    -0.07
    our
    -0.06
    ####
    -0.06
    _PUSHDATA
    -0.06
    "',
    -0.06
     "',
    -0.06
    atırım
    -0.06
    ۲
    -0.06
     tế
    -0.06
    POSITIVE LOGITS
     toward
    0.12
     percent
    0.11
     Percent
    0.10
     canceled
    0.09
     theater
    0.09
    _gray
    0.09
     afterward
    0.09
    -gray
    0.08
     labeled
    0.08
     burned
    0.08
    Act Density 0.100%

    No Known Activations