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

    Neuronpedia

    INDEX
    Explanations

    character descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags mentions that a character is based on or inspired by a real‐life person.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .getBoolean
    -0.07
     CY
    -0.07
     yabancı
    -0.06
    807
    -0.06
    sigma
    -0.06
    .prot
    -0.06
     modifies
    -0.06
     kính
    -0.06
    рабат
    -0.06
     Yet
    -0.06
    POSITIVE LOGITS
     damning
    0.07
    ennen
    0.06
     apparently
    0.06
     RAID
    0.06
    _checkpoint
    0.06
     glac
    0.06
     Talking
    0.06
     Continental
    0.06
    <Customer
    0.06
     ayak
    0.05
    Act Density 0.097%

    No Known Activations