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

    Neuronpedia

    INDEX
    Explanations

    good performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    šit
    2.77
    hoea
    2.77
    ouncement
    2.75
    囝
    2.73
     calendário
    2.66
    organised
    2.62
     adjournment
    2.61
     مصرى
    2.61
     منصوبہ
    2.59
    딧
    2.57
    POSITIVE LOGITS
    7
    2.93
    6
    2.63
    8
    2.56
    3
    2.47
    4
    2.44
    5
    2.26
    9
    2.12
     Leb
    2.08
     K
    2.07
    2
    2.06
    Act Density 0.154%

    No Known Activations