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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (digits and numbers, including decimal‐formatted values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     henüz
    -0.07
     gz
    -0.07
     ↵
    -0.07
     лю
    -0.07
    Qu
    -0.07
     desperately
    -0.07
    .eng
    -0.06
     Qu
    -0.06
    .lon
    -0.06
    _TIM
    -0.06
    POSITIVE LOGITS
    Doctrine
    0.07
    Transfer
    0.06
    Characters
    0.06
    _advance
    0.06
    enza
    0.06
    _invite
    0.06
     prejudice
    0.06
    zz
    0.06
    atican
    0.06
    ymoon
    0.06
    Act Density 0.245%

    No Known Activations