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

    Neuronpedia

    INDEX
    Explanations

    plus

    np_max-act · gemini-2.0-flash

    This neuron is effectively dead—it never activates on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mun
    -0.07
     požadav
    -0.07
     Grey
    -0.07
     Sheridan
    -0.06
    Logged
    -0.06
    .biz
    -0.06
    onds
    -0.06
    _MAN
    -0.06
    ashtra
    -0.06
     füh
    -0.06
    POSITIVE LOGITS
    ?>"><
    0.07
    =<?=
    0.07
     özg
    0.06
    +"<
    0.06
    отор
    0.06
    ؟↵
    0.06
    Forg
    0.06
    ลาย
    0.06
     reduce
    0.06
     accordion
    0.06
    Act Density 0.010%

    No Known Activations