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

    Neuronpedia

    INDEX
    Explanations

    Gemma team at Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ierge
    0.70
    harga
    0.68
    िशा
    0.62
    sep
    0.60
     ಔ
    0.58
    센
    0.58
    ௐ
    0.57
     क्वीन
    0.57
    浐
    0.57
     लवकर
    0.56
    POSITIVE LOGITS
    Dest
    0.54
     தண்ட
    0.52
     Rub
    0.51
     rub
    0.51
     rubbing
    0.50
     Gemma
    0.50
     Dest
    0.50
     ரீ
    0.49
    Rub
    0.48
    ixas
    0.48
    Act Density 0.227%

    No Known Activations