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

    Neuronpedia

    INDEX
    Explanations

    scents and contamination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yata
    -0.09
    .UTC
    -0.08
    ustatud
    -0.08
    íoch
    -0.08
    itza
    -0.08
    ysize
    -0.08
    yä
    -0.07
    یمت
    -0.07
    )){
    -0.07
    .mvp
    -0.07
    POSITIVE LOGITS
     mingle
    0.12
     unintended
    0.11
     contamination
    0.11
     contaminación
    0.11
     inadvert
    0.11
     inadvertently
    0.11
     overlapping
    0.10
    污染
    0.10
     unrelated
    0.10
     contamin
    0.10
    Act Density 0.047%

    No Known Activations