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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _aa
    -0.07
     usr
    -0.07
    结石
    -0.07
    שטח
    -0.07
    @mail
    -0.06
    HashTable
    -0.06
    لب
    -0.06
    .Persistent
    -0.06
    替え
    -0.06
    :start
    -0.06
    POSITIVE LOGITS
    侍
    0.08
    _TRAN
    0.07
    _ROUT
    0.07
    nob
    0.07
    ()["
    0.07
     western
    0.06
    <void
    0.06
    綦
    0.06
    עביר
    0.06
     incons
    0.06
    Act Density 0.148%

    No Known Activations