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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Article
    -0.07
    .pdf
    -0.07
    ..........
    -0.07
     Inspir
    -0.06
    貂
    -0.06
    称为
    -0.06
    _MISSING
    -0.06
    ṇ
    -0.06
     sisters
    -0.06
     Setting
    -0.06
    POSITIVE LOGITS
     escal
    0.09
    !');↵
    0.07
    .actions
    0.07
    London
    0.07
     strerror
    0.07
     بكل
    0.07
     bicycles
    0.07
    .unlock
    0.07
    สภาพ
    0.07
    🧘
    0.06
    Act Density 0.014%

    No Known Activations