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

    Neuronpedia

    INDEX
    Explanations

    probably the most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hydraulic
    0.33
    Types
    0.32
    antation
    0.32
    ம்தான்
    0.31
    >
    0.31
     subprocess
    0.31
    rugated
    0.31
     Shipbuilding
    0.31
    ⌋
    0.30
     traversing
    0.30
    POSITIVE LOGITS
     exaggerate
    0.44
     ogni
    0.44
     unfairly
    0.42
    ותר
    0.42
    最も
    0.42
     cliché
    0.42
     całej
    0.41
     exager
    0.40
     svih
    0.38
     every
    0.38
    Act Density 0.100%

    No Known Activations