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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _charge
    -0.07
     gamer
    -0.07
    타
    -0.07
     Break
    -0.06
    ,(
    -0.06
    =C
    -0.06
     र
    -0.06
     orient
    -0.06
    -Free
    -0.06
    陸
    -0.06
    POSITIVE LOGITS
    ']):↵
    0.07
     DIFF
    0.07
    .cd
    0.06
     plaint
    0.06
     str
    0.06
     babel
    0.06
    lear
    0.06
     low
    0.06
     early
    0.06
    Cheers
    0.06
    Act Density 0.000%

    No Known Activations