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

    Neuronpedia

    INDEX
    Explanations

    booking tickets to skip lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ្នាក់
    0.39
     busses
    0.39
    oths
    0.38
     freezes
    0.36
    unicode
    0.35
    ूंगा
    0.35
    })=\
    0.35
    aretro
    0.35
    sendLog
    0.34
    outgoing
    0.34
    POSITIVE LOGITS
    Skip
    0.56
     skip
    0.54
     Skip
    0.51
     temprano
    0.48
    skip
    0.47
     hassle
    0.44
     convenient
    0.42
    kách
    0.42
    毗
    0.41
    സു
    0.40
    Act Density 0.002%

    No Known Activations