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

    Neuronpedia

    INDEX
    Explanations

    common connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    軟
    -0.08
     gate
    -0.07
     fabricated
    -0.07
     цар
    -0.07
    ANJI
    -0.07
    Price
    -0.07
     sensitive
    -0.06
    ียม
    -0.06
     representation
    -0.06
    .bool
    -0.06
    POSITIVE LOGITS
    文章
    0.07
    Slash
    0.07
    _positive
    0.06
    Skipping
    0.06
     assignable
    0.06
    нивер
    0.06
     vượt
    0.06
    ',(
    0.06
     Converted
    0.06
    	define
    0.06
    Act Density 0.086%

    No Known Activations