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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    78
    -0.07
    _O
    -0.07
    18
    -0.06
     epsilon
    -0.06
     Dimensions
    -0.06
    75
    -0.06
    88
    -0.06
    _corner
    -0.06
     cents
    -0.06
     přik
    -0.06
    POSITIVE LOGITS
    HasBeen
    0.08
     decltype
    0.07
    "
↵
↵
↵
    0.07
     Subjects
    0.07
    accounts
    0.07
     Changes
    0.07
     хочу
    0.07
     textual
    0.07
    templates
    0.07
    achsen
    0.07
    Act Density 0.188%

    No Known Activations