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

    Neuronpedia

    INDEX
    Explanations

    technical issues and errors

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that describe the user’s attempt to deposit or make a payment.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gems
    -0.07
     hä
    -0.07
    gt
    -0.06
    род
    -0.06
    Skills
    -0.06
    etě
    -0.06
    ení
    -0.06
    sess
    -0.06
    比
    -0.06
     Zero
    -0.06
    POSITIVE LOGITS
    Journal
    0.07
     eliminar
    0.06
     علاوه
    0.06
    SEA
    0.06
     conhe
    0.06
    �认
    0.06
     resetting
    0.06
    ostringstream
    0.06
    restrial
    0.06
     transforms
    0.06
    Act Density 0.020%

    No Known Activations