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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valley
    -0.06
     nacional
    -0.06
     addicts
    -0.06
    :utf
    -0.06
     laminate
    -0.06
     })↵
    -0.06
     junction
    -0.06
     Nigel
    -0.06
    ταν
    -0.06
    .Dataset
    -0.06
    POSITIVE LOGITS
    (',',$
    0.07
    Monthly
    0.07
    _expression
    0.07
    dio
    0.07
    rone
    0.07
     intric
    0.07
     Ου
    0.06
     повинен
    0.06
     Excellent
    0.06
     Operating
    0.06
    Act Density 0.031%

    No Known Activations