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

    Neuronpedia

    INDEX
    Explanations

    select, copy, drop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اوز
    0.45
     आयोजित
    0.44
     Plummer
    0.42
     playerScore
    0.40
    اؤ
    0.39
     پلا
    0.39
    ㈡
    0.38
     secondNumber
    0.38
    ashore
    0.38
    觞
    0.38
    POSITIVE LOGITS
    mn
    0.39
     bp
    0.38
     Tod
    0.37
     /*
    0.35
     succ
    0.35
    bp
    0.34
     localhost
    0.34
     p
    0.34
     P
    0.34
     bd
    0.34
    Act Density 0.001%

    No Known Activations