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

    Neuronpedia

    INDEX
    Explanations

    creation and production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    제를
    0.45
     dealings
    0.44
     развитие
    0.43
    ப்பே
    0.42
     combing
    0.42
     humiliating
    0.42
     ಆಯ್
    0.41
     apoyo
    0.41
     działania
    0.41
     apoio
    0.40
    POSITIVE LOGITS
    ，
    0.47
    ،
    0.44
    ,
    0.43
    であろう
    0.40
     (
    0.36
    തും
    0.36
     microorganisms
    0.35
     شدہ
    0.35
    、
    0.35
    드의
    0.34
    Act Density 0.109%

    No Known Activations