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

    Neuronpedia

    INDEX
    Explanations

    event names and progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ges
    0.46
    ்க
    0.44
     तथा
    0.43
     તથા
    0.42
     ಹಾಗೂ
    0.40
    ös
    0.40
    拟
    0.40
    擬
    0.39
    密的
    0.39
    பாய்
    0.39
    POSITIVE LOGITS
     Linton
    0.47
     selfish
    0.46
     coton
    0.46
     vittime
    0.44
    !’
    0.44
     Jenna
    0.43
     Coldplay
    0.43
    ！」
    0.43
    !”
    0.42
     slippers
    0.41
    Act Density 0.000%

    No Known Activations