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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hå
    -0.07
    _sh
    -0.07
    _mot
    -0.07
    洛
    -0.07
    ("(%
    -0.06
    _fee
    -0.06
     qualification
    -0.06
     HomePage
    -0.06
    ροι
    -0.06
    GINE
    -0.06
    POSITIVE LOGITS
     ult
    0.06
     Zusammen
    0.06
    .chomp
    0.06
     Tv
    0.06
    ple
    0.06
    umuz
    0.06
     programma
    0.06
     UserProfile
    0.06
     buddy
    0.06
    (separator
    0.06
    Act Density 0.015%

    No Known Activations