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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vacant
    -0.08
    伸手
    -0.08
    DateTime
    -0.07
    Ṫ
    -0.07
    @Api
    -0.07
     iq
    -0.07
    evt
    -0.07
     Kum
    -0.07
    usaha
    -0.07
    項目
    -0.07
    POSITIVE LOGITS
     фор
    0.08
     soldiers
    0.08
     audits
    0.07
     Scots
    0.07
     Nice
    0.07
    董
    0.07
     compl
    0.07
    )';↵
    0.07
    прод
    0.07
     cycl
    0.07
    Act Density 0.019%

    No Known Activations