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

    Neuronpedia

    INDEX
    Explanations

    code and markup languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     탐
    -0.07
     تنها
    -0.06
     Ты
    -0.06
    นส
    -0.06
    }.↵
    -0.06
     deposits
    -0.06
    .wav
    -0.06
     документа
    -0.06
    }px
    -0.06
    ]]↵↵
    -0.06
    POSITIVE LOGITS
    贝
    0.07
    calling
    0.07
    cond
    0.06
    	Common
    0.06
    _band
    0.06
     fName
    0.06
    .Sql
    0.06
    settings
    0.06
    elog
    0.06
     unrealistic
    0.06
    Act Density 0.015%

    No Known Activations