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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RIGHT
    -0.07
    }-${
    -0.06
    Roll
    -0.06
     funds
    -0.06
     organise
    -0.06
     anchor
    -0.06
     NIC
    -0.05
     organize
    -0.05
     typo
    -0.05
     stopwords
    -0.05
    POSITIVE LOGITS
     能
    0.07
     Ví
    0.07
     сут
    0.07
    ˜
    0.06
    -eslint
    0.06
    roupon
    0.06
    ilecek
    0.06
    ℃
    0.06
     ozone
    0.06
    ちは
    0.06
    Act Density 0.348%

    No Known Activations