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

    Neuronpedia

    INDEX
    Explanations

    sports, study, cats, diversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiddos
    0.77
     badass
    0.73
     underwhelming
    0.70
     moniker
    0.68
     inherently
    0.65
     workaround
    0.65
     Leveraging
    0.63
     leveraging
    0.62
     shenanigans
    0.62
     bolstering
    0.62
    POSITIVE LOGITS
     newspapers
    0.64
     businessmen
    0.64
    spapers
    0.59
     policemen
    0.58
     famous
    0.57
     clothes
    0.55
    clothes
    0.55
     Businessman
    0.54
     berühm
    0.52
     spoilt
    0.52
    Act Density 0.020%

    No Known Activations