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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on Russian adjectives (i.e. words with adjective‐type endings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ume
    -0.08
     Fe
    -0.07
    .compose
    -0.07
    de
    -0.07
    DE
    -0.07
    Je
    -0.07
    796
    -0.07
    ke
    -0.06
     Yue
    -0.06
     SCE
    -0.06
    POSITIVE LOGITS
    ный
    0.08
    _any
    0.08
     одной
    0.08
    ой
    0.07
    ¤¤
    0.07
    щий
    0.07
     responder
    0.07
    ий
    0.07
     Checker
    0.07
    サイ
    0.07
    Act Density 0.078%

    No Known Activations