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

    Neuronpedia

    INDEX
    Explanations

    personal risk/sacrifice

    np_max-act · gemini-2.0-flash

    This neuron activates on words describing personal cost–benefit trade‐offs (e.g. “personal,” “costs,” “benefit”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     btc
    -0.07
     Reach
    -0.07
    iscopal
    -0.06
     PROGRAM
    -0.06
    _DEL
    -0.06
     Adolescent
    -0.06
     plunge
    -0.06
     об
    -0.06
     conscience
    -0.06
    _free
    -0.06
    POSITIVE LOGITS
    もしれない
    0.06
     هناك
    0.06
    Clause
    0.06
     /*<<<
    0.06
     secretly
    0.06
    τιο
    0.06
    NamedQuery
    0.06
     Salem
    0.06
    EIF
    0.06
    rowData
    0.06
    Act Density 0.052%

    No Known Activations