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

    Neuronpedia

    INDEX
    Explanations

    based on / regardless of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     That
    0.21
    ®.
    0.18
     It
    0.18
     This
    0.17
    center
    0.17
     When
    0.17
     There
    0.16
    There
    0.16
     Draper
    0.15
     Wasn
    0.15
    POSITIVE LOGITS
    ของการ
    0.21
    䏹
    0.20
     usability
    0.20
     մ
    0.19
     scalability
    0.19
     relat
    0.19
     ganas
    0.19
     robustness
    0.19
    jasama
    0.18
     unor
    0.18
    Act Density 0.176%

    No Known Activations