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

    Neuronpedia

    INDEX
    Explanations

    Procrastination

    np_max-act · gemini-2.0-flash

    This neuron detects the subword “procrast” (as in “procrastination”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     servicio
    -0.07
    朋
    -0.06
    독
    -0.06
     nack
    -0.06
    .locals
    -0.06
     detection
    -0.06
     metabolism
    -0.06
     TZ
    -0.06
     descent
    -0.06
     GitHub
    -0.06
    POSITIVE LOGITS
    crast
    0.10
     procrast
    0.10
    fin
    0.06
    .↵↵↵
    0.06
     xhr
    0.06
    olut
    0.06
    ").↵↵
    0.06
    ertia
    0.06
    (Constants
    0.06
     Kasich
    0.06
    Act Density 0.002%

    No Known Activations