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

    Neuronpedia

    INDEX
    Explanations

    depends on size and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lontano
    0.41
     irgendwo
    0.38
     provare
    0.35
     дале
    0.34
    झ्या
    0.33
     machining
    0.33
    steuer
    0.33
    zler
    0.33
    шеб
    0.32
    RIC
    0.32
    POSITIVE LOGITS
     crews
    0.36
    طلاع
    0.34
     dismissal
    0.34
     アイアン
    0.33
    дзі
    0.33
     sit
    0.33
    complexity
    0.33
     walkers
    0.33
     treat
    0.32
    ựa
    0.32
    Act Density 0.002%

    No Known Activations