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

    Neuronpedia

    INDEX
    Explanations

    strategies and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的同时
    0.42
    Gall
    0.41
    很
    0.40
    ῎
    0.40
    When
    0.39
    。”
    0.39
    下
    0.38
    List
    0.38
    ார
    0.38
    จะ
    0.37
    POSITIVE LOGITS
     Sheikh
    0.49
     कोविड
    0.48
     linf
    0.47
     eines
    0.46
     TUN
    0.46
     Himalayas
    0.45
     MBA
    0.45
     suivants
    0.45
     Nurs
    0.44
     unfolding
    0.44
    Act Density 0.007%

    No Known Activations