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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    This neuron detects phrasing that expresses an imminent or inevitable future event (often a negative outcome), especially constructions like “a matter of time before ….”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inu
    -0.07
    Reusable
    -0.07
     så
    -0.07
    ємо
    -0.06
     Phú
    -0.06
    //================================================================================
    -0.06
    Unique
    -0.06
    Recv
    -0.06
     Smoking
    -0.06
     "").
    -0.06
    POSITIVE LOGITS
     scratches
    0.07
     underst
    0.07
     dps
    0.07
     kids
    0.06
    asyarak
    0.06
    BTTagCompound
    0.06
     ('
    0.06
    /lab
    0.06
    .getJSONArray
    0.06
    reglo
    0.06
    Act Density 0.014%

    No Known Activations