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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꯋ
    0.40
     rehearsals
    0.39
     юбилей
    0.39
    ய்
    0.38
     drums
    0.38
     कुशलता
    0.37
     harte
    0.37
    源
    0.37
    Java
    0.36
     Graphs
    0.36
    POSITIVE LOGITS
    oglio
    0.46
    ಗಳಿಗೆ
    0.40
    WithName
    0.40
     עם
    0.40
    毕竟
    0.39
    کری
    0.39
    umphed
    0.39
    ים
    0.39
    માં
    0.39
    孩子们
    0.39
    Act Density 0.004%

    No Known Activations