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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron never actually activates on any token—i.e. it’s effectively “dead” and doesn’t detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    OTH
    -0.07
    —"
    -0.07
    cannot
    -0.07
    、「
    -0.07
    ();
↵
↵
↵
    -0.06
     mentally
    -0.06
     Born
    -0.06
    comment
    -0.06
    ồng
    -0.06
     volunteered
    -0.06
    POSITIVE LOGITS
     유
    0.07
     Tage
    0.07
     lavender
    0.06
     './../
    0.06
     ir
    0.06
     vår
    0.06
     дерева
    0.06
    olicited
    0.06
     republik
    0.06
    Backdrop
    0.06
    Act Density 0.005%

    No Known Activations