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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the word “console,” i.e. when the text refers to gaming consoles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (encoding
    -0.06
    cpu
    -0.06
     -------
    -0.06
    px
    -0.06
    -Clause
    -0.06
    ionage
    -0.06
     CI
    -0.06
     TB
    -0.06
    ney
    -0.06
     Jobs
    -0.06
    POSITIVE LOGITS
     SYN
    0.07
    ariance
    0.07
     MAIL
    0.06
    ğer
    0.06
    teil
    0.06
    _DR
    0.06
    Anc
    0.06
     Nickel
    0.06
    parameter
    0.06
    _BOX
    0.06
    Act Density 0.110%

    No Known Activations