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

    Neuronpedia

    INDEX
    Explanations

    code and section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cecil
    0.37
     Dad
    0.37
     대로
    0.37
    dan
    0.36
    वणी
    0.36
     sfai
    0.35
    ❐
    0.35
    대로
    0.34
     speichern
    0.34
     கட்டடக்கலை
    0.34
    POSITIVE LOGITS
    study
    0.76
     study
    0.75
    Study
    0.71
     Study
    0.70
     estudo
    0.65
     estudio
    0.57
     STUDY
    0.57
     étude
    0.57
    étude
    0.55
     अध्ययन
    0.54
    Act Density 0.000%

    No Known Activations