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

    Neuronpedia

    INDEX
    Explanations

    overflow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pointer
    -0.06
    post
    -0.06
     دستگاه
    -0.06
    .Token
    -0.06
     George
    -0.06
     münchen
    -0.06
    isation
    -0.06
    @nate
    -0.06
     rat
    -0.06
     konkrét
    -0.06
    POSITIVE LOGITS
     overflow
    0.09
    .overflow
    0.08
     highways
    0.07
    offs
    0.07
    loff
    0.07
     unpack
    0.07
    orn
    0.07
     mushrooms
    0.07
    _overflow
    0.07
     wells
    0.07
    Act Density 0.002%

    No Known Activations