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

    Neuronpedia

    INDEX
    Explanations

    shrimp and shrink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Süden
    -2.73
     legions
    -2.56
     Personally
    -2.56
     They
    -2.52
     exhilar
    -2.50
     Not
    -2.50
     maverick
    -2.47
     glittering
    -2.44
    +.
    -2.42
     nhưng
    -2.41
    POSITIVE LOGITS
    虓
    2.89
    釓
    2.64
    秕
    2.59
    you
    2.56
     fantástica
    2.53
    鹬
    2.52
    茕
    2.48
    笮
    2.48
    "+
    2.47
    猡
    2.47
    Act Density 0.001%

    No Known Activations