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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash

    This neuron responds to the “hope that it will be useful, but WITHOUT ANY WARRANTY” boilerplate in license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    상
    -0.06
    sWith
    -0.06
    _PARAM
    -0.06
     policies
    -0.06
    Interactive
    -0.06
     Μέ
    -0.06
    THOOK
    -0.06
    nak
    -0.06
    yaw
    -0.06
    상을
    -0.06
    POSITIVE LOGITS
     +-
    0.07
                                    ↵
    0.07
    ;/*
    0.07
     --->
    0.07
    *",
    0.06
    """
↵
↵
    0.06
     Mu
    0.06
    ([
↵
    0.06
     "*
    0.06
    /*↵
    0.06
    Act Density 0.005%

    No Known Activations