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

    Neuronpedia

    INDEX
    Explanations

    instructions or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tranche
    0.30
     dechlorination
    0.29
     eigenfunctions
    0.29
     superconductors
    0.25
     heals
    0.25
     thiol
    0.25
     paws
    0.24
     superpowers
    0.24
     cocon
    0.24
     că
    0.24
    POSITIVE LOGITS
    While
    0.36
    Although
    0.35
     Although
    0.35
     गौरतलब
    0.35
     While
    0.34
     Regardless
    0.34
    As
    0.31
     Since
    0.31
     Throughout
    0.31
     Organizing
    0.31
    Act Density 0.001%

    No Known Activations