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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probably
    -0.08
    脍
    -0.07
    />
    -0.07
     grain
    -0.07
    .Windows
    -0.07
     insanely
    -0.07
    ߡ
    -0.07
    .This
    -0.07
    这部电影
    -0.07
     أخي
    -0.07
    POSITIVE LOGITS
    "<?
    0.08
     pav
    0.08
    设定
    0.07
     newX
    0.07
    الط
    0.07
    .ALL
    0.07
    .cwd
    0.07
    AJOR
    0.07
     TOD
    0.07
    _IMPL
    0.07
    Act Density 0.001%

    No Known Activations