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

    Neuronpedia

    INDEX
    Explanations

    panic

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on mentions of “panic,” particularly in the context of “panic attacks.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ràng
    -0.07
     лист
    -0.07
    Rows
    -0.07
    _slave
    -0.07
     rib
    -0.06
     slee
    -0.06
     �
    -0.06
    isors
    -0.06
    _bounds
    -0.06
    کل
    -0.06
    POSITIVE LOGITS
     panic
    0.14
     Panic
    0.13
     panicked
    0.09
    libc
    0.08
     Quick
    0.08
     political
    0.07
    _SYSTEM
    0.07
     frantic
    0.07
    	panic
    0.07
     pry
    0.07
    Act Density 0.001%

    No Known Activations