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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hạ
    -0.07
    物
    -0.07
     getopt
    -0.06
    ittance
    -0.06
    -sup
    -0.06
     wealthiest
    -0.06
     indentation
    -0.06
     explo
    -0.06
     вода
    -0.06
     knowingly
    -0.06
    POSITIVE LOGITS
    aisy
    0.07
     razor
    0.06
     inspector
    0.06
     rush
    0.06
     inevitably
    0.06
    ček
    0.06
     demeanor
    0.06
     accurate
    0.05
     Secure
    0.05
    _equ
    0.05
    Act Density 0.019%

    No Known Activations