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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .xtext
    -0.08
     metav
    -0.07
     području
    -0.07
    示
    -0.07
     య
    -0.07
    .endpoint
    -0.07
    ary
    -0.07
    .variables
    -0.07
     elimination
    -0.07
    kezt
    -0.07
    POSITIVE LOGITS
     vinyl
    0.10
     Beethoven
    0.09
     Mint
    0.09
    τί
    0.08
     Half
    0.08
     Vinyl
    0.08
     проиг
    0.08
     cláss
    0.08
     انتخاب
    0.08
     मालिक
    0.08
    Act Density 0.010%

    No Known Activations