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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bedo
    0.49
    headings
    0.47
    ⟋
    0.47
     fundamento
    0.44
     ಅಭಿಮಾನ
    0.44
     pillars
    0.43
     hendak
    0.43
     totalSupply
    0.43
    cparam
    0.42
     digestive
    0.42
    POSITIVE LOGITS
     Paxton
    0.43
    }$;
    0.40
    sters
    0.40
     Grade
    0.40
    Learning
    0.40
     Pak
    0.38
     Pan
    0.38
    }$\
    0.38
     fair
    0.38
     Learn
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.