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

    Neuronpedia

    INDEX
    Explanations

    highway, driving, trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VEN
    0.40
     смотрите
    0.40
     있지만
    0.40
    ЕН
    0.39
    이지만
    0.38
     เช่น
    0.37
     ヨ
    0.37
    GBuf
    0.36
     поради
    0.36
    Ло
    0.36
    POSITIVE LOGITS
    mainframe
    0.44
    Ii
    0.40
    ledem
    0.40
    问题的
    0.40
     broadly
    0.39
    粝
    0.38
    gist
    0.37
    ྜ
    0.37
     την
    0.37
    cedures
    0.37
    Act Density 0.000%

    No Known Activations