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

    Neuronpedia

    INDEX
    Explanations

    counting or numbering items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Equals
    1.16
    ও
    1.08
    iare
    1.00
    PIPE
    0.97
    不及
    0.97
    很难
    0.94
    ALSO
    0.94
    cdots
    0.93
    vee
    0.93
    ++
    0.92
    POSITIVE LOGITS
    ي
    1.53
    i
    1.48
    י
    1.38
    ⿷
    1.37
    y
    1.28
    bies
    1.28
    ি
    1.27
    睬
    1.26
    courses
    1.23
    apeutics
    1.18
    Act Density 0.000%

    No Known Activations