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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ાડ
    1.30
    이
    1.30
    ה
    1.27
    Ѡ
    1.27
    \)
    1.22
    ০
    1.22
    شهر
    1.19
    т
    1.18
     pikiran
    1.18
     comté
    1.17
    POSITIVE LOGITS
     ruins
    1.11
     whistles
    1.07
    Reload
    1.06
    us
    1.06
    ef
    1.03
    اری
    1.01
     favorably
    1.01
    loads
    1.01
    ARY
    0.99
     замеча
    0.97
    Act Density 0.000%

    No Known Activations