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

    Neuronpedia

    INDEX
    Explanations

    machine

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it never produces a nonzero activation on any input tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Objects
    -0.07
     Florian
    -0.07
     зараз
    -0.06
     dol
    -0.06
     bonds
    -0.06
     northeast
    -0.06
    Jam
    -0.06
     Scots
    -0.06
    InvalidOperationException
    -0.06
     Why
    -0.06
    POSITIVE LOGITS
    ocab
    0.07
     Machine
    0.07
     banc
    0.07
     IPv
    0.07
    皆
    0.06
    ("↵
    0.06
    lesc
    0.06
     modele
    0.06
    orestation
    0.06
     met
    0.06
    Act Density 0.009%

    No Known Activations