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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imat
    -0.07
     retr
    -0.07
    辒
    -0.07
    オススメ
    -0.06
    ("-",
    -0.06
    五月
    -0.06
    veis
    -0.06
     opioids
    -0.06
    emme
    -0.06
     bugün
    -0.06
    POSITIVE LOGITS
    otted
    0.07
     Industry
    0.07
    structors
    0.07
    歌手
    0.07
    -html
    0.07
    Protected
    0.07
    protocol
    0.07
     spoken
    0.06
    接口
    0.06
    industry
    0.06
    Act Density 0.123%

    No Known Activations