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
     Calgary
    -0.07
    /sign
    -0.06
    993
    -0.06
     truyền
    -0.06
    Bal
    -0.06
    709
    -0.06
     Vice
    -0.06
    721
    -0.06
    .ref
    -0.06
    filesystem
    -0.06
    POSITIVE LOGITS
     maneuver
    0.07
     име
    0.07
    (TokenType
    0.07
    attendance
    0.07
     arous
    0.06
     τους
    0.06
     aile
    0.06
     jaké
    0.06
     cla
    0.06
     goodwill
    0.06
    Act Density 0.118%

    No Known Activations