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

    Neuronpedia

    INDEX
    Explanations

    Barnaby's descriptive interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    単純
    0.57
     sympt
    0.57
     analges
    0.56
     vicious
    0.56
    😒
    0.56
     deceit
    0.55
     generalizations
    0.54
     uneas
    0.53
     prur
    0.53
     generalizing
    0.53
    POSITIVE LOGITS
     mascot
    0.73
     iconic
    0.72
     commemorated
    0.71
     यादगार
    0.70
     commemorative
    0.68
     quirky
    0.67
     celebrated
    0.66
    Celebrating
    0.66
     themed
    0.65
     знамени
    0.65
    Act Density 0.087%

    No Known Activations