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

    Neuronpedia

    INDEX
    Explanations

    shift

    np_max-act · gemini-2.0-flash

    This neuron detects numeric literal constants (e.g. hex or decimal values) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    however
    -0.07
     코드
    -0.07
     gatherings
    -0.07
     wil
    -0.07
     Eric
    -0.06
    Sci
    -0.06
     Cat
    -0.06
    efa
    -0.06
     tělo
    -0.06
     watering
    -0.06
    POSITIVE LOGITS
     فو
    0.06
    lx
    0.06
     pretrained
    0.06
    ]]↵↵
    0.06
     redefine
    0.06
    propertyName
    0.06
    cribing
    0.06
    одерж
    0.06
     jMenuItem
    0.06
    toggle
    0.06
    Act Density 0.003%

    No Known Activations