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

    Neuronpedia

    INDEX
    Explanations

    json, datetime, date, timestamp, report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ளும்
    0.54
    iją
    0.53
     vendeur
    0.51
     Golden
    0.50
    ίου
    0.49
     loan
    0.48
     templo
    0.48
     Porsche
    0.47
     Giordano
    0.46
    elight
    0.46
    POSITIVE LOGITS
    LT
    0.50
    Observe
    0.49
    CCOCC
    0.49
    Reduce
    0.48
    ittees
    0.47
    Mixin
    0.47
    ARD
    0.47
    lj
    0.47
    خ
    0.47
    मौसम
    0.47
    Act Density 0.000%

    No Known Activations