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

    Neuronpedia

    INDEX
    Explanations

    equals signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lebanese
    -0.07
     kidd
    -0.06
    /'.$
    -0.06
    692
    -0.06
    離
    -0.06
     ambiance
    -0.06
     Kidd
    -0.06
    <Type
    -0.06
    tons
    -0.06
     chees
    -0.06
    POSITIVE LOGITS
     المللی
    0.07
     Logging
    0.07
     mystery
    0.06
    .AWS
    0.06
     aggress
    0.06
     DON
    0.06
    ettings
    0.06
    .ALL
    0.06
     attacker
    0.06
     leaves
    0.06
    Act Density 0.034%

    No Known Activations