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

    Neuronpedia

    INDEX
    Explanations

    full lace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scanning
    0.87
     Scanning
    0.86
    Science
    0.84
     scanned
    0.82
    Survey
    0.82
    scanning
    0.78
     Object
    0.78
    Web
    0.77
     Science
    0.76
     நுண்ண
    0.75
    POSITIVE LOGITS
     scandals
    0.95
     famously
    0.94
     romances
    0.93
     flamboyant
    0.91
     infamous
    0.91
     populer
    0.89
     cosidd
    0.88
     rojos
    0.88
     popularized
    0.87
     prostitutes
    0.87
    Act Density 2.195%

    No Known Activations