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

    Neuronpedia

    INDEX
    Explanations

    communication, questions, problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beschikbaar
    0.37
     beschik
    0.36
     constituer
    0.36
     essenti
    0.35
     verkrij
    0.35
     eenvoud
    0.34
     activiteiten
    0.34
     zowel
    0.34
     technologie
    0.34
     bestaat
    0.34
    POSITIVE LOGITS
    moi
    0.34
    really
    0.32
     really
    0.29
     moi
    0.29
     bisschen
    0.29
     opravdu
    0.28
    Maybe
    0.27
    maybe
    0.27
     vrai
    0.27
    Contours
    0.26
    Act Density 0.002%

    No Known Activations