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

    Neuronpedia

    INDEX
    Explanations

    Associates

    np_max-act · gemini-2.0-flash

    The neuron detects affiliate disclosure language, especially mentions of the Amazon Services/Associates Program.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    čila
    -0.07
    _PRI
    -0.07
     shirt
    -0.07
     brushing
    -0.06
    _CAM
    -0.06
    .WinForms
    -0.06
    -либо
    -0.06
     desper
    -0.06
     グ
    -0.06
    icers
    -0.06
    POSITIVE LOGITS
    (My
    0.07
     )"
    0.07
    rans
    0.06
    àng
    0.06
     Cascade
    0.06
    ames
    0.06
    nement
    0.06
     防
    0.06
     pulp
    0.06
     ++)
    0.06
    Act Density 0.001%

    No Known Activations