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

    Neuronpedia

    INDEX
    Explanations

    Scientific data

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numerical measurement expressions (numbers with units or parameter values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LOCKS
    -0.06
     dus
    -0.06
     آینده
    -0.06
     combining
    -0.06
     Ga
    -0.06
    Develop
    -0.06
     Hank
    -0.06
    ulence
    -0.05
    MISSION
    -0.05
    ुज
    -0.05
    POSITIVE LOGITS
    .Relative
    0.07
     sayı
    0.06
     河
    0.06
    +c
    0.06
    ":"",↵
    0.06
     очевид
    0.06
     розгля
    0.06
     norsk
    0.06
    template
    0.06
    áo
    0.06
    Act Density 0.038%

    No Known Activations