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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    The neuron is responding to numeric literals (integer or decimal) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DIR
    -0.07
    MYSQL
    -0.07
     ingen
    -0.07
     
    -0.07
    _ACTIV
    -0.06
     قض
    -0.06
    และม
    -0.06
    ,↵↵
    -0.06
    ,↵
    -0.06
    ...
↵
    -0.06
    POSITIVE LOGITS
    asy
    0.07
     Bers
    0.07
     Personal
    0.07
    lear
    0.07
     Rad
    0.06
    _CAP
    0.06
     inter
    0.06
    TableView
    0.06
     Actor
    0.06
     reciprocal
    0.06
    Act Density 0.005%

    No Known Activations