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

    Neuronpedia

    INDEX
    Explanations

    break keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused755>
    0.61
    extrait
    0.61
    RELATIVA
    0.59
    Ⲕ
    0.59
    Ethoxy
    0.58
    getSub
    0.58
    Ⲃ
    0.57
    Gav
    0.57
    𒂗
    0.57
    Whatever
    0.57
    POSITIVE LOGITS
      
    0.84
     a
    0.69
    <0xC2>
    0.69
     and
    0.64
    ,
    0.63
     ​​
    0.63
       
    0.63
     break
    0.62
    0.61
     the
    0.61
    Act Density 0.681%

    No Known Activations