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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Php
    -0.08
     trap
    -0.07
     break
    -0.07
    ())/
    -0.07
    𬘘
    -0.07
    荁
    -0.07
     Poke
    -0.07
    icers
    -0.06
    ธาน
    -0.06
    Rank
    -0.06
    POSITIVE LOGITS
    任
    0.08
     fundamentally
    0.07
    十二
    0.07
    臂
    0.07
     שינוי
    0.07
     statistically
    0.07
     encoded
    0.07
     EVENT
    0.07
     OM
    0.07
    <m
    0.07
    Act Density 0.003%

    No Known Activations