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

    Neuronpedia

    INDEX
    Explanations

    400

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    」↵↵
    -0.07
    .Pl
    -0.07
     Constit
    -0.06
     칼
    -0.06
     methodologies
    -0.06
     letters
    -0.06
    -0.06
     ReadOnly
    -0.06
    (Func
    -0.06
    POSITIVE LOGITS
    250
    0.08
    90
    0.08
    220
    0.07
    890
    0.07
    100
    0.07
    80
    0.07
    10
    0.07
    400
    0.07
     noci
    0.07
    70
    0.07
    Act Density 0.031%

    No Known Activations