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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric tokens (i.e., numbers with a fractional part) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tém
    -0.07
     '_',
    -0.06
    ANDROID
    -0.06
     Như
    -0.06
    consult
    -0.06
    _PHYS
    -0.06
     neust
    -0.06
    298
    -0.06
     будто
    -0.06
    angi
    -0.06
    POSITIVE LOGITS
     Genel
    0.07
     Кар
    0.07
     UN
    0.06
     Он
    0.06
     blog
    0.06
    �
    0.06
     �
    0.06
     edits
    0.06
    ItemSelected
    0.06
    .Local
    0.06
    Act Density 0.020%

    No Known Activations