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

    Neuronpedia

    INDEX
    Explanations

    manually

    np_max-act · gemini-2.0-flash

    references to database management and configuration processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Eating
    -0.07
     frase
    -0.07
     Firmware
    -0.06
     那
    -0.06
    _spot
    -0.06
    .places
    -0.06
     punctuation
    -0.06
    _pop
    -0.06
     Egyptians
    -0.06
    RR
    -0.06
    POSITIVE LOGITS
     σει
    0.07
     звичай
    0.07
     lov
    0.06
    .tm
    0.06
    indeki
    0.06
     vin
    0.06
    angelo
    0.06
    alleries
    0.06
     manten
    0.06
    ensely
    0.06
    Act Density 0.016%

    No Known Activations