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

    Neuronpedia

    INDEX
    Explanations

    electronic components

    np_max-act · gemini-2.0-flash

    The neuron responds to technical component and part names in patent‐style descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     printed
    -0.07
    printed
    -0.07
    ιστή
    -0.06
     Cro
    -0.06
    positor
    -0.06
     Such
    -0.06
     SEM
    -0.06
     pe
    -0.06
     oppressive
    -0.06
    _ar
    -0.06
    POSITIVE LOGITS
     подход
    0.07
    Explicit
    0.07
    Flags
    0.07
     Initialized
    0.06
     Roosevelt
    0.06
    Ж
    0.06
     �
    0.06
    ango
    0.06
    >:
    0.06
     �
    0.06
    Act Density 0.062%

    No Known Activations