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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the interrogative “who” (i.e. questions asking about a person).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Daniels
    -0.08
     overflow
    -0.07
     fprintf
    -0.06
     生
    -0.06
    افع
    -0.06
     flag
    -0.06
    _books
    -0.06
    sterreich
    -0.06
     Det
    -0.06
    Dia
    -0.06
    POSITIVE LOGITS
     corre
    0.07
    :pk
    0.07
    ues
    0.06
    /User
    0.06
    camera
    0.06
    .tasks
    0.06
    zilla
    0.06
    格
    0.06
     accuses
    0.06
    	initialize
    0.06
    Act Density 0.017%

    No Known Activations