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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron responds to tokens that are floating-point numbers (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    generic
    -0.07
    onClick
    -0.07
    atitude
    -0.07
    -of
    -0.07
    Boom
    -0.07
    ogo
    -0.06
    infile
    -0.06
    Topology
    -0.06
     rebuilt
    -0.06
    الق
    -0.06
    POSITIVE LOGITS
     compartments
    0.07
     Intr
    0.07
                       ↵
    0.07
     Stuart
    0.07
     javax
    0.06
     dziewcz
    0.06
     McMaster
    0.06
     ikt
    0.06
     жир
    0.06
     Bạn
    0.06
    Act Density 0.050%

    No Known Activations