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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning terminology and notation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÐIJÑĢÑħÑĸв
    -0.08
     Qed
    -0.07
    resh
    -0.07
    edenÃŃ
    -0.06
    .LA
    -0.06
    etti
    -0.06
    -ÑĤо
    -0.06
    abal
    -0.06
    ystore
    -0.06
     Donne
    -0.06
    POSITIVE LOGITS
    olie
    0.06
    ince
    0.06
    gence
    0.06
    ramid
    0.06
    лам
    0.06
    vana
    0.05
    rut
    0.05
    ,},↵
    0.05
    ektor
    0.05
    plemented
    0.05
    Act Density 0.110%

    No Known Activations