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

    Neuronpedia

    INDEX
    Explanations

    compiled program or executable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्स
    0.81
    wind
    0.72
    ted
    0.71
    nominated
    0.70
    suff
    0.68
    ammatory
    0.67
    ͆
    0.67
    tooltip
    0.66
    sentation
    0.65
    изо
    0.65
    POSITIVE LOGITS
     Fase
    0.81
     Disk
    0.79
     Shazam
    0.79
     Faites
    0.78
     Kroger
    0.75
     Fass
    0.75
    㘿
    0.75
     thúc
    0.75
     Choisissez
    0.74
     Slave
    0.73
    Act Density 0.004%

    No Known Activations