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

    Neuronpedia

    INDEX
    Explanations

    lack, absence, negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ักษณะ
    0.37
    roughly
    0.35
    டுவது
    0.35
    Ⴎ
    0.34
    totalPages
    0.33
    Lore
    0.32
    ળે
    0.32
    ⴼ
    0.32
    ändern
    0.32
     voire
    0.32
    POSITIVE LOGITS
     unfortunately
    0.76
     Unable
    0.74
    残念
    0.74
     unable
    0.73
     Unfortunately
    0.73
     sadly
    0.73
     Sadly
    0.73
     missed
    0.69
     lacked
    0.68
     leider
    0.68
    Act Density 0.252%

    No Known Activations