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

    Neuronpedia

    INDEX
    Explanations

    calculus functions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LHS
    0.44
     Curie
    0.41
     AB
    0.41
     «
    0.39
    形成的
    0.39
     $|\
    0.38
     abelian
    0.38
    «
    0.38
     Literature
    0.38
     shape
    0.37
    POSITIVE LOGITS
    ruv
    0.44
     combatir
    0.43
    खा
    0.42
     क्लियर
    0.42
    鈽
    0.42
    Nick
    0.40
    >());
    0.39
    Bingo
    0.39
     クリア
    0.39
    竑
    0.38
    Act Density 0.017%

    No Known Activations