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

    Neuronpedia

    INDEX
    Explanations

    commander of the RSF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     breakage
    0.75
     configuration
    0.75
     ingestion
    0.73
     carbur
    0.73
     siga
    0.72
     tensile
    0.70
     schematic
    0.70
     absorbance
    0.70
     setup
    0.68
     deviation
    0.67
    POSITIVE LOGITS
     whom
    0.96
     Emeritus
    0.92
     emeritus
    0.92
    université
    0.82
     Riverside
    0.82
     Planet
    0.80
     Manchester
    0.78
    whom
    0.77
     extraordinaire
    0.75
     Ghana
    0.74
    Act Density 0.086%

    No Known Activations