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

    Neuronpedia

    INDEX
    Explanations

    multi-paradigma languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dT
    0.46
     Improving
    0.45
    ೂರ್
    0.43
    шої
    0.42
     Useful
    0.42
    anée
    0.42
    Improving
    0.42
    Useful
    0.42
    ীবনী
    0.41
     Vanden
    0.41
    POSITIVE LOGITS
     piens
    0.52
     pons
    0.50
     signific
    0.50
     ron
    0.48
    ет
    0.47
    ،
    0.47
     procura
    0.46
    ت
    0.46
     mogelijk
    0.46
     processions
    0.45
    Act Density 0.003%

    No Known Activations