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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سن
    -0.07
     عبدالله
    -0.07
    _SN
    -0.07
    FFFFFF
    -0.07
    渰
    -0.06
    sar
    -0.06
    _NV
    -0.06
    haft
    -0.06
     naz
    -0.06
    ính
    -0.06
    POSITIVE LOGITS
    ]'↵
    0.09
    ières
    0.08
    顶
    0.07
     elő
    0.07
    jectory
    0.07
     boiling
    0.07
    /software
    0.07
     "]
    0.07
    人性
    0.07
    𝗲
    0.06
    Act Density 0.000%

    No Known Activations