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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on occurrences of the token “test” (in any capitalization).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _MOUSE
    -0.08
    _IGNORE
    -0.07
     ITS
    -0.06
    PYTHON
    -0.06
     Vys
    -0.06
    ISTER
    -0.06
    .flatMap
    -0.06
    Touchable
    -0.06
     lobbyist
    -0.06
    .viewmodel
    -0.06
    POSITIVE LOGITS
     Serial
    0.07
     attempting
    0.06
    �
    0.06
     win
    0.06
     play
    0.06
     outputFile
    0.06
    -pro
    0.06
     jasmine
    0.06
     demonstrated
    0.06
    账
    0.06
    Act Density 0.017%

    No Known Activations