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

    Neuronpedia

    INDEX
    Explanations

    introduces a concept or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    映
    0.40
    ܗ
    0.40
     готови
    0.39
     ನಡುವ
    0.39
    é
    0.39
    બો
    0.39
    閆
    0.39
     вопрос
    0.38
    0.38
    હ
    0.38
    POSITIVE LOGITS
     institu
    0.38
     wrinkle
    0.37
     EPA
    0.36
    న్ని
    0.35
     Chrysler
    0.35
     Drugs
    0.35
     institute
    0.35
     Ciencias
    0.35
     Institute
    0.35
     biotechn
    0.35
    Act Density 0.000%

    No Known Activations