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

    Neuronpedia

    INDEX
    Explanations

    to appoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MOT
    0.14
    Rit
    0.13
     وه
    0.13
    ційний
    0.12
     символ
    0.12
    ନ
    0.12
     simbolo
    0.12
     alone
    0.12
     thôi
    0.12
     lễ
    0.12
    POSITIVE LOGITS
     Espero
    0.15
     Sword
    0.14
    elic
    0.14
     Новости
    0.13
     Și
    0.13
     Außerdem
    0.13
    baru
    0.13
     menonton
    0.13
     CELL
    0.13
     Sper
    0.13
    Act Density 0.000%

    No Known Activations