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

    Neuronpedia

    INDEX
    Explanations

    ax

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive (a “dead” neuron) and does not respond to any input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    separator
    -0.07
    '\
    -0.07
    _grp
    -0.07
     belts
    -0.07
    _Set
    -0.07
     bus
    -0.06
     pus
    -0.06
    	string
    -0.06
    計
    -0.06
     caus
    -0.06
    POSITIVE LOGITS
     сот
    0.07
    icho
    0.07
     आज
    0.06
     insets
    0.06
     الاح
    0.06
    นอ
    0.06
     lĩnh
    0.06
     prés
    0.06
    EPS
    0.06
     aimed
    0.06
    Act Density 0.004%

    No Known Activations