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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sâu
    -0.08
     Latter
    -0.07
     느
    -0.07
     Village
    -0.07
     NST
    -0.07
    	fr
    -0.07
     pense
    -0.07
    (cli
    -0.07
     singular
    -0.07
    YG
    -0.07
    POSITIVE LOGITS
    🐃
    0.07
     Kickstarter
    0.07
    运
    0.07
    早点加盟
    0.07
    好不容易
    0.07
    <uint
    0.06
    ┰
    0.06
    Actually
    0.06
    ust
    0.06
     leukemia
    0.06
    Act Density 0.024%

    No Known Activations