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

    Neuronpedia

    INDEX
    Explanations

    something profound, unexpected, or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annoying
    0.34
     پرت
    0.33
     boring
    0.31
     funny
    0.31
    उदा
    0.30
     cute
    0.29
     ditth
    0.29
     obnoxious
    0.29
     intimidating
    0.29
     pesky
    0.28
    POSITIVE LOGITS
     bigger
    0.38
     others
    0.36
     greater
    0.35
    greater
    0.35
    bigger
    0.34
    ധികം
    0.33
    Others
    0.33
     beyond
    0.32
     extraordinary
    0.32
     nobody
    0.31
    Act Density 0.017%

    No Known Activations