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

    Neuronpedia

    INDEX
    Explanations

    please read important notes/disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    था
    0.38
    ,
    0.37
     মেয়াদ
    0.37
    لا
    0.36
    lgende
    0.35
     whopping
    0.32
    য়া
    0.32
    Mc
    0.31
     διάρκεια
    0.31
     لە
    0.30
    POSITIVE LOGITS
     ihn
    0.40
    nent
    0.39
    and
    0.39
     aidant
    0.38
     ogl
    0.38
    them
    0.37
     Он
    0.37
    ২৮
    0.37
     Liste
    0.36
     them
    0.36
    Act Density 0.016%

    No Known Activations