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

    Neuronpedia

    INDEX
    Explanations

    verbs after commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ,
    0.81
    ၊
    0.80
    ，
    0.77
    ،
    0.75
     ،
    0.70
    ፣
    0.68
     there
    0.68
    .,
    0.64
    。,
    0.62
    ​,
    0.61
    POSITIVE LOGITS
     mutta
    0.49
     letzt
    0.48
    ly
    0.48
    中でも
    0.46
    FirstOrDefault
    0.44
     پھر
    0.44
    f
    0.43
    setName
    0.42
    \
    0.42
     X
    0.41
    Act Density 0.045%

    No Known Activations