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

    Neuronpedia

    INDEX
    Explanations

    temperature difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мыкты
    0.41
     courthouse
    0.40
     коричне
    0.40
     potrzeby
    0.39
     تعليم
    0.39
     maksymal
    0.38
    duğ
    0.38
     ameryka
    0.38
    iędzy
    0.38
     راجس
    0.38
    POSITIVE LOGITS
     solid
    0.43
     remo
    0.42
     carrier
    0.41
     prolong
    0.40
    移動
    0.40
     bread
    0.39
     container
    0.39
    ik
    0.39
     carriers
    0.38
     Solid
    0.38
    Act Density 0.080%

    No Known Activations