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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nvidia
    -0.07
    GD
    -0.06
    लग
    -0.06
    484
    -0.06
     PUS
    -0.06
    ména
    -0.06
    .Throw
    -0.06
    _nn
    -0.06
     Ä
    -0.06
    ou
    -0.06
    POSITIVE LOGITS
    езд
    0.06
    -support
    0.06
     соответствии
    0.06
    (undefined
    0.06
     Reference
    0.06
    )/(
    0.06
     affiliated
    0.06
     getSource
    0.06
     Incorrect
    0.06
     EventEmitter
    0.06
    Act Density 0.350%

    No Known Activations