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

    Neuronpedia

    INDEX
    Explanations

    Russia making support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хар
    0.44
     formando
    0.44
    蛊
    0.43
     intégral
    0.42
    )]),
    0.41
    --");
    0.41
     arme
    0.39
     çık
    0.39
     théorie
    0.39
     strang
    0.39
    POSITIVE LOGITS
    un
    0.55
    um
    0.54
    lovers
    0.52
     to
    0.50
    ung
    0.50
    el
    0.49
     was
    0.49
    isset
    0.49
    ectors
    0.49
    rists
    0.49
    Act Density 0.001%

    No Known Activations