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

    Neuronpedia

    INDEX
    Explanations

    im followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hab
    0.96
    indices
    0.92
     Monique
    0.90
     getValue
    0.88
     absolute
    0.86
     obten
    0.85
     generalization
    0.85
     היי
    0.84
     маши
    0.84
    ssid
    0.83
    POSITIVE LOGITS
    जेंसी
    1.21
    ſelf
    1.08
    돠
    1.02
    ح
    1.00
    daad
    1.00
    ேத்க
    0.99
    prints
    0.98
    othy
    0.97
    ério
    0.97
    printing
    0.96
    Act Density 0.338%

    No Known Activations