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

    Neuronpedia

    INDEX
    Explanations

    dot

    np_max-act · gemini-2.0-flash

    The neuron is activated by occurrences of the literal string “dot” (in any case) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Rei
    -0.07
     Refugee
    -0.07
     wives
    -0.07
     Reese
    -0.07
    Ware
    -0.07
     Weiner
    -0.07
     Age
    -0.07
     Milwaukee
    -0.07
     Schwe
    -0.06
     Wilhelm
    -0.06
    POSITIVE LOGITS
     dot
    0.13
     Dot
    0.11
    Dot
    0.11
    -dot
    0.09
    dot
    0.09
    _dot
    0.09
    ot
    0.09
    Ds
    0.08
    .dot
    0.08
     dots
    0.08
    Act Density 0.008%

    No Known Activations