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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash

    This neuron activates on the hypnotist’s formal spoken commands or addresses (e.g. “Ladies,” “Gentlemen,” “Normally,” “Now”) in the dialogue.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mounting
    -0.07
    Func
    -0.07
    LEM
    -0.06
     jin
    -0.06
    reas
    -0.06
     Subway
    -0.06
    ارک
    -0.06
     gia
    -0.06
    HW
    -0.06
    _accessor
    -0.06
    POSITIVE LOGITS
    otherapy
    0.07
    _typeDefinitionSize
    0.07
     слыш
    0.06
    (URL
    0.06
     quieres
    0.06
     allow
    0.06
    oll
    0.06
     Allies
    0.06
     recoil
    0.06
    ..'
    0.06
    Act Density 0.005%

    No Known Activations