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

    Neuronpedia

    INDEX
    Explanations

    path through, fantastic descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bandit
    0.49
     суток
    0.49
     sudut
    0.46
     lucro
    0.45
    balik
    0.44
     funzioni
    0.44
     Yaad
    0.44
     escenario
    0.43
     climático
    0.43
     regioni
    0.42
    POSITIVE LOGITS
    นั่ง
    0.45
    ၉
    0.45
    String
    0.44
     একট
    0.44
    ი
    0.43
    经
    0.43
    経
    0.42
    ラベル
    0.41
     ۹
    0.41
    勻
    0.40
    Act Density 0.002%

    No Known Activations