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

    Neuronpedia

    INDEX
    Explanations

    answering question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }↵
    -0.07
     DUI
    -0.06
    _result
    -0.06
     Assad
    -0.06
    repeat
    -0.06
     Im
    -0.06
    Systems
    -0.06
     декабря
    -0.06
    Click
    -0.06
     tuning
    -0.06
    POSITIVE LOGITS
    KANJI
    0.07
     двер
    0.06
    ışı
    0.06
     bombers
    0.06
     thous
    0.06
     тва
    0.06
     因
    0.06
     десят
    0.06
    诊
    0.06
    毎
    0.06
    Act Density 0.258%

    No Known Activations