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

    Neuronpedia

    INDEX
    Explanations

    numbers and ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snippets
    -0.06
     Me
    -0.06
    isia
    -0.06
    itles
    -0.06
    -income
    -0.06
    .hm
    -0.06
     steward
    -0.06
    =B
    -0.06
     Authority
    -0.06
     delayed
    -0.05
    POSITIVE LOGITS
     noche
    0.07
    NSDictionary
    0.07
    '):↵
    0.07
     trẻ
    0.06
    Tôi
    0.06
    este
    0.06
    .gameserver
    0.06
     BELOW
    0.06
    zig
    0.06
     обличчя
    0.06
    Act Density 0.188%

    No Known Activations