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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    files related to software licensing and documentation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects “Author” lines (the author metadata) in source‐code file headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gré
    -0.07
     bpp
    -0.06
     grille
    -0.06
     disciple
    -0.06
    .sidebar
    -0.06
    431
    -0.06
    객
    -0.06
     vaše
    -0.06
    .COM
    -0.06
     Borough
    -0.06
    POSITIVE LOGITS
     восстанов
    0.07
     Transformers
    0.07
    ENAME
    0.07
     [['
    0.07
     sucking
    0.06
     Atomic
    0.06
     Polic
    0.06
    (Output
    0.06
    Initialization
    0.06
     �
    0.06
    Act Density 0.009%

    No Known Activations