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

    Neuronpedia

    INDEX
    Explanations

    Medical abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CERT
    -0.07
    갔
    -0.07
     показ
    -0.07
    estation
    -0.07
     الحي
    -0.07
     noted
    -0.07
    为之
    -0.07
     shows
    -0.07
    言って
    -0.07
     ragazze
    -0.07
    POSITIVE LOGITS
     sinus
    0.07
    Uluslararası
    0.07
    otron
    0.07
    ประส
    0.07
    中新
    0.07
     vari
    0.07
    搦
    0.07
    选拔
    0.06
    渑
    0.06
    ประชา
    0.06
    Act Density 0.052%

    No Known Activations