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

    Neuronpedia

    INDEX
    Explanations

    following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ("
    0.86
     struggling
    0.81
     allegedly
    0.78
     nearly
    0.78
     gifted
    0.76
     grieving
    0.73
     teeming
    0.72
     purportedly
    0.71
     Indians
    0.71
     almost
    0.70
    POSITIVE LOGITS
    ,
    2.01
    ،
    1.54
    、
    1.48
    ，
    1.45
    ,-
    1.40
    ፣
    1.31
    ,%
    1.30
    ,{
    1.30
    ,/
    1.29
     ,
    1.28
    Act Density 0.000%

    No Known Activations