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

    Neuronpedia

    INDEX
    Explanations

    joining lists with `and`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opss
    0.67
     arrhythmias
    0.64
    깆
    0.64
    などを
    0.64
    arlı
    0.64
     ইত্যাদি
    0.62
    などに
    0.62
     jetty
    0.62
     প্রভৃতির
    0.62
    alaikums
    0.61
    POSITIVE LOGITS
     :
    0.74
    .
    0.73
    ::
    0.70
    。
    0.70
     。
    0.63
     simultaneously
    0.59
     โดย
    0.59
     because
    0.59
     Sweden
    0.59
    /
    0.59
    Act Density 0.540%

    No Known Activations