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

    Neuronpedia

    INDEX
    Explanations

    ear tip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    编码
    0.41
    σον
    0.40
    біць
    0.40
    स्पर
    0.39
    rı
    0.37
    ിട
    0.36
    冲击
    0.36
    ጣጠ
    0.36
    шым
    0.35
    耠
    0.35
    POSITIVE LOGITS
    0.33
     thro
    0.33
    /
    0.33
     despair
    0.33
     g
    0.32
    ,
    0.32
     Dr
    0.32
     greater
    0.32
     fencing
    0.32
    *
    0.32
    Act Density 0.000%

    No Known Activations