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

    Neuronpedia

    INDEX
    Explanations

    selection from lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जब
    0.37
     использовании
    0.36
     নামক
    0.36
    ्याच्या
    0.35
     Ninety
    0.35
     данным
    0.35
     மற்றொரு
    0.35
     যাবে
    0.34
     دش
    0.34
    uscany
    0.34
    POSITIVE LOGITS
    包括
    0.60
    =['
    0.57
     all
    0.57
     alles
    0.57
     includ
    0.55
    すべて
    0.54
    哪些
    0.54
     lahat
    0.53
     everything
    0.53
    すべての
    0.52
    Act Density 0.056%

    No Known Activations