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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Colorado
    -0.07
    "^
    -0.07
    사회
    -0.06
    ँ
    -0.06
    ABCDE
    -0.06
    .url
    -0.06
     tedav
    -0.06
     груп
    -0.06
     offended
    -0.06
    .lazy
    -0.06
    POSITIVE LOGITS
     assignments
    0.07
     silently
    0.07
     ornaments
    0.07
     Pharma
    0.07
     Leah
    0.06
     residues
    0.06
    .Then
    0.06
     oppon
    0.06
     races
    0.06
    bugs
    0.06
    Act Density 0.084%

    No Known Activations