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

    Neuronpedia

    INDEX
    Explanations

    gap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     archivo
    -0.08
    author
    -0.07
     Manufacturers
    -0.07
    smith
    -0.07
    doll
    -0.07
    Wood
    -0.07
    鲁
    -0.07
     والد
    -0.07
     manufacture
    -0.07
     couleur
    -0.06
    POSITIVE LOGITS
     gap
    0.14
     Gap
    0.14
     gaps
    0.12
     GAP
    0.10
    _GAP
    0.10
    Gap
    0.09
    gap
    0.09
    -gap
    0.09
     lag
    0.08
    ерах
    0.08
    Act Density 0.007%

    No Known Activations