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

    Neuronpedia

    INDEX
    Explanations

    action or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이차
    0.50
    یک
    0.49
     अधिनियम
    0.49
     incluir
    0.47
    ون
    0.47
     יד
    0.47
    프
    0.45
    ्रिक
    0.45
     들어가
    0.44
     integrar
    0.44
    POSITIVE LOGITS
    guessed
    0.47
     southbound
    0.45
    guesses
    0.45
    decode
    0.44
    MnO
    0.44
    bacteria
    0.42
    thirty
    0.41
    kbd
    0.41
    0.41
     باذن
    0.41
    Act Density 0.001%

    No Known Activations