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

    Neuronpedia

    INDEX
    Explanations

    NSObject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ALLENG
    -0.07
     змож
    -0.07
     смерти
    -0.06
     сьогодні
    -0.06
     Dud
    -0.06
    過
    -0.06
    layarak
    -0.06
    ців
    -0.06
    .Identifier
    -0.06
    osopher
    -0.06
    POSITIVE LOGITS
    NSObject
    0.15
     NSObject
    0.07
    Shared
    0.07
     token
    0.07
     Ramsey
    0.07
     posed
    0.06
    \Contracts
    0.06
    (NS
    0.06
     prince
    0.06
    \File
    0.06
    Act Density 0.000%

    No Known Activations