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

    Neuronpedia

    INDEX
    Explanations

    X1 Carbon and X1 Yoga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łoż
    0.49
     zwięks
    0.49
    φέρει
    0.48
     détail
    0.48
    եղ
    0.47
     contrôler
    0.47
     Storia
    0.47
    نٹ
    0.45
    رود
    0.45
    ر
    0.45
    POSITIVE LOGITS
    ចេញ
    0.54
    eye
    0.50
     insignia
    0.48
    បង្ហាញ
    0.47
    say
    0.45
    est
    0.44
    law
    0.44
    ARD
    0.44
     eye
    0.44
    have
    0.43
    Act Density 0.000%

    No Known Activations