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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _contract
    -0.07
    允
    -0.07
    anus
    -0.07
    .pretty
    -0.07
    應
    -0.07
     solution
    -0.06
    successfully
    -0.06
     president
    -0.06
     rhyme
    -0.06
     Fakültesi
    -0.06
    POSITIVE LOGITS
     }//
    0.07
    ?-
    0.06
    dbuf
    0.06
    [])
    0.06
    RO
    0.06
     //*
    0.06
     таб
    0.06
     огром
    0.06
    şı
    0.06
     mi
    0.06
    Act Density 0.013%

    No Known Activations