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

    Neuronpedia

    INDEX
    Explanations

    lots of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்துடன்
    0.41
    yrıca
    0.38
     వివిధ
    0.38
    டுகளை
    0.38
    helps
    0.37
    ագ
    0.37
    कई
    0.37
     יע
    0.37
     मेला
    0.36
    imde
    0.36
    POSITIVE LOGITS
    ،
    0.52
    ,
    0.47
    ，
    0.46
     that
    0.45
    that
    0.41
    :
    0.41
     instrumentality
    0.40
     :=
    0.38
    ՝
    0.38
     (!)
    0.37
    Act Density 0.013%

    No Known Activations