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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自己在
    0.39
    aczego
    0.38
    ---
    0.36
    Ꮩ
    0.34
    ᅳ
    0.34
    Wires
    0.32
    urts
    0.32
    ancer
    0.32
    смотреть
    0.31
    Inbox
    0.31
    POSITIVE LOGITS
     uniformity
    0.37
     Mr
    0.37
     букмекерлик
    0.37
    sqlUpdate
    0.37
     Lukaku
    0.35
    glClear
    0.35
     জঙ্গ
    0.34
     fraternity
    0.34
    হাট
    0.34
     Odinga
    0.33
    Act Density 0.104%

    No Known Activations