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

    Neuronpedia

    INDEX
    Explanations

    disrupting information or comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larında
    1.41
    단의
    1.34
     оказалась
    1.31
    Harper
    1.28
     решила
    1.24
    larının
    1.23
    이를
    1.23
    ют
    1.23
    larını
    1.21
     目前
    1.21
    POSITIVE LOGITS
    ed
    1.13
     ৬৬
    1.10
     abras
    1.10
     Lash
    1.09
    alag
    1.08
    ਡ
    1.03
    fung
    1.03
    edian
    1.03
     ব্যবস্থাপ
    1.03
    us
    1.02
    Act Density 0.000%

    No Known Activations