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

    Neuronpedia

    INDEX
    Explanations

    code licensing

    np_max-act · gemini-2.0-flash

    The neuron activates whenever it sees the substring “lit” (e.g. in “Streamlit”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    responseObject
    -0.08
     transporter
    -0.07
    //================================================
    -0.07
     vestib
    -0.06
    unnel
    -0.06
    :e
    -0.06
     �
    -0.06
    endale
    -0.06
     feud
    -0.06
    /********************************************************
    -0.06
    POSITIVE LOGITS
    baar
    0.07
     Points
    0.07
     ****
    0.07
     starting
    0.07
     Penguins
    0.06
    前
    0.06
     Whole
    0.06
    iedy
    0.06
    ???↵↵
    0.06
     extremely
    0.06
    Act Density 0.000%

    No Known Activations