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

    Neuronpedia

    INDEX
    Explanations

    commentary after **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.51
     tabindex
    0.47
    ্সর
    0.41
    PhD
    0.40
     attenu
    0.39
     pharmacists
    0.39
    دام
    0.39
     informatics
    0.38
    דיו
    0.38
    Chemistry
    0.38
    POSITIVE LOGITS
     Hike
    0.52
     которого
    0.47
    ovým
    0.45
     Backpack
    0.45
    ankar
    0.42
    chers
    0.42
     Peacock
    0.42
     Beetle
    0.42
     jednot
    0.42
    wreck
    0.42
    Act Density 0.004%

    No Known Activations