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

    Neuronpedia

    INDEX
    Explanations

    lists and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engender
    0.36
    ซึ่ง
    0.35
    particularly
    0.34
     zejména
    0.33
    undered
    0.33
     sobretudo
    0.33
     έ
    0.33
    ඥ
    0.32
     markedly
    0.31
     insbesondere
    0.31
    POSITIVE LOGITS
    ials
    0.42
     lf
    0.39
     HAVING
    0.38
     paypal
    0.37
    ings
    0.37
     अगर
    0.36
     Behind
    0.35
    이스
    0.35
     behind
    0.35
    ของการ
    0.34
    Act Density 3.920%

    No Known Activations