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

    Neuronpedia

    INDEX
    Explanations

    advertising, lodging, commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circled
    0.41
    ávání
    0.40
    ਤਰ
    0.38
    peace
    0.38
     peacefully
    0.38
     obsz
    0.37
    opez
    0.37
    [[
    0.37
     perten
    0.37
    াতের
    0.36
    POSITIVE LOGITS
     Wisdom
    0.38
    hetical
    0.36
    Crash
    0.35
    니다
    0.34
    INDI
    0.34
     কতকগুলি
    0.34
     elaborate
    0.34
    หุ้น
    0.33
    理
    0.33
    indi
    0.33
    Act Density 0.000%

    No Known Activations