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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron flags tokens that are parts of clock‐time expressions (hours, minutes, or the colon in “H:MM” style times).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    达到
    -0.07
    UIS
    -0.07
     comfort
    -0.06
     ""}↵
    -0.06
     землю
    -0.06
     Gore
    -0.06
     Ok
    -0.06
    -grid
    -0.06
     paste
    -0.06
     مرک
    -0.06
    POSITIVE LOGITS
    ΥΡ
    0.07
     smě
    0.06
     _{}
    0.06
    ्ण
    0.06
     Tories
    0.06
     пар
    0.06
     процессе
    0.06
    irsch
    0.06
     cursed
    0.06
    ifik
    0.06
    Act Density 0.002%

    No Known Activations