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

    Neuronpedia

    INDEX
    Explanations

    function followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    0.97
     keď
    0.82
    ொருள்
    0.79
     म्हणूनच
    0.79
    ঙ্গি
    0.77
     //
    0.76
     certainly
    0.75
     صح
    0.75
     Komponenten
    0.75
    ➔
    0.75
    POSITIVE LOGITS
    (){
    1.27
    aries
    1.03
    unteers
    1.02
    onium
    0.97
    iquement
    0.97
    naire
    0.95
    টিকে
    0.92
    wounded
    0.91
    बाद
    0.91
    टीम
    0.89
    Act Density 0.030%

    No Known Activations