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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =",
    -0.07
     heterogeneous
    -0.06
    _colour
    -0.06
    }"
    -0.06
    brands
    -0.06
    Develop
    -0.06
     customizable
    -0.06
    -0.06
    stdin
    -0.06
    šov
    -0.06
    POSITIVE LOGITS
     loses
    0.07
    进入
    0.07
     losing
    0.07
    mobx
    0.06
     مش
    0.06
    .toArray
    0.06
     schn
    0.06
    мент
    0.06
     veel
    0.06
    Bush
    0.06
    Act Density 0.008%

    No Known Activations