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

    Neuronpedia

    INDEX
    Explanations

    difficult experiences

    np_max-act · gemini-2.0-flash

    This neuron activates on second-person, empathetic statements describing the reader’s personal involvement in an accident or injury (e.g., “being involved in an accident may be troubling you a lot;”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Black
    -0.07
     Black
    -0.07
    747
    -0.06
    -0.06
    .back
    -0.06
     طریق
    -0.06
    HexString
    -0.06
    803
    -0.06
    _CBC
    -0.06
     Beats
    -0.06
    POSITIVE LOGITS
    teness
    0.06
     partes
    0.06
     extortion
    0.06
    entreprise
    0.06
    pek
    0.06
    IRONMENT
    0.06
     burnt
    0.06
     fread
    0.06
     Egyptians
    0.06
     Attribution
    0.06
    Act Density 0.062%

    No Known Activations