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

    Neuronpedia

    INDEX
    Explanations

    specific items and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    0.44
    div
    0.44
    lla
    0.40
     रोकने
    0.40
     Jind
    0.40
    et
    0.39
    ub
    0.39
    decompose
    0.38
    nergy
    0.38
    চেতন
    0.37
    POSITIVE LOGITS
     verbal
    0.39
     terribly
    0.39
     ا
    0.39
     approved
    0.39
     amazingly
    0.38
     term
    0.37
     presentations
    0.37
    િન
    0.37
     ataxia
    0.37
     devast
    0.37
    Act Density 0.009%

    No Known Activations