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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens containing decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cellular
    -0.07
     chess
    -0.06
     〈
    -0.06
    澳
    -0.06
    ано
    -0.06
     دوست
    -0.06
    OrderId
    -0.06
    .EVENT
    -0.06
    Algorithm
    -0.06
     Booth
    -0.06
    POSITIVE LOGITS
     행동
    0.07
    �
    0.07
    .",
↵
    0.07
     строк
    0.07
    kwargs
    0.06
    λαμβ
    0.06
    .relu
    0.06
     forward
    0.06
    .jdesktop
    0.06
     ]
↵
    0.06
    Act Density 0.000%

    No Known Activations