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

    Neuronpedia

    INDEX
    Explanations

    280

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (digits and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infants
    -0.06
    .TH
    -0.06
     CODE
    -0.06
    -ev
    -0.06
    .MEDIA
    -0.06
    ﾟ
    -0.06
     جزء
    -0.06
    cpy
    -0.06
    χεία
    -0.06
     αυτά
    -0.06
    POSITIVE LOGITS
     Accounting
    0.07
     Barg
    0.07
     лож
    0.07
     brainstorm
    0.07
     GIT
    0.06
    neğin
    0.06
     Frost
    0.06
     Prison
    0.06
     chương
    0.06
     sos
    0.06
    Act Density 0.004%

    No Known Activations