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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    스터
    -0.08
    言葉
    -0.07
    incinn
    -0.07
    sticks
    -0.07
     gó
    -0.06
    таж
    -0.06
     inner
    -0.06
     Litecoin
    -0.06
    _DETECT
    -0.06
    .'/'.$
    -0.06
    POSITIVE LOGITS
     Fog
    0.07
    (userData
    0.07
     가입
    0.07
     roman
    0.07
    ↵ ↵
    0.07
    覆
    0.07
    افته
    0.06
          
    0.06
    онах
    0.06
    arena
    0.06
    Act Density 0.000%

    No Known Activations