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

    Neuronpedia

    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens that include a decimal point (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suicide
    -0.08
    _pdf
    -0.07
    _rad
    -0.07
     online
    -0.07
     Rating
    -0.07
    راد
    -0.07
     recommended
    -0.07
    Suffix
    -0.06
    unnable
    -0.06
    Cost
    -0.06
    POSITIVE LOGITS
    ého
    0.06
    /item
    0.06
    ndx
    0.06
    koliv
    0.06
    Containing
    0.06
     dol
    0.06
    .IsAny
    0.06
     elektrik
    0.06
     перем
    0.06
     rencontr
    0.06
    Act Density 0.001%

    No Known Activations