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

    Neuronpedia

    INDEX
    Explanations

    snippets with 'n'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ently
    0.37
    年会
    0.36
    otic
    0.36
     yearbook
    0.36
     MPa
    0.35
     bella
    0.34
     Gross
    0.34
     Andrew
    0.34
     Regional
    0.34
     regional
    0.33
    POSITIVE LOGITS
    ཋ
    0.46
    ፩
    0.44
    Buck
    0.41
    ップ
    0.38
    텝
    0.38
     समानार्थी
    0.38
    箴
    0.38
    AMAN
    0.38
    수인
    0.38
    तम
    0.37
    Act Density 0.041%

    No Known Activations