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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (quantities) in mathematical word-problem contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Attached
    -0.07
     �
    -0.06
     FF
    -0.06
    ırı
    -0.06
    _allocator
    -0.06
    UserID
    -0.06
     pris
    -0.06
    Bang
    -0.06
    coil
    -0.06
     attn
    -0.06
    POSITIVE LOGITS
     withdraw
    0.07
     amaç
    0.07
     Οκ
    0.06
     Licence
    0.06
    OS
    0.06
    elly
    0.06
     проф
    0.06
     POSIX
    0.06
     Narc
    0.06
    ropriate
    0.06
    Act Density 0.028%

    No Known Activations