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

    Neuronpedia

    INDEX
    Explanations

    word fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .emptyList
    -0.07
     akce
    -0.06
    rání
    -0.06
    iect
    -0.06
     Sob
    -0.06
    }",
    -0.06
     reject
    -0.06
     mg
    -0.06
    _bits
    -0.06
     팬
    -0.06
    POSITIVE LOGITS
    Syntax
    0.07
     obliv
    0.07
    кас
    0.07
     oblivious
    0.07
     unbearable
    0.06
    scanner
    0.06
    stin
    0.06
    かな
    0.06
    県
    0.06
    then
    0.06
    Act Density 0.027%

    No Known Activations