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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the token “on” when it appears as part of a switch-on command (e.g. “turn on”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     和
    -0.06
    _POST
    -0.06
     engr
    -0.06
     Floors
    -0.06
    ;width
    -0.06
    pole
    -0.06
    ivé
    -0.06
     isot
    -0.06
    =list
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ínu
    0.07
    UIImage
    0.07
    zzarella
    0.07
     UIImage
    0.07
     inconsistent
    0.07
    λου
    0.06
     Scientology
    0.06
     perspective
    0.06
    .viewModel
    0.06
    ({},
    0.06
    Act Density 0.006%

    No Known Activations