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

    Neuronpedia

    INDEX
    Explanations

    German sentence end

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     looks
    0.73
     insights
    0.71
     circa
    0.70
     residents
    0.69
     insight
    0.68
     orders
    0.67
     premiers
    0.66
     Floral
    0.66
     stars
    0.65
     leads
    0.65
    POSITIVE LOGITS
    ändert
    0.71
    Writable
    0.71
    gebung
    0.68
    ähne
    0.66
    ertung
    0.65
    weiß
    0.65
    uliert
    0.64
    elung
    0.64
    achel
    0.62
    uerung
    0.62
    Act Density 0.001%

    No Known Activations