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

    Neuronpedia

    INDEX
    Explanations

    "D: Defendant" or "If/Would" clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complements
    0.68
     ranges
    0.65
     samples
    0.64
     inspiration
    0.64
     inspires
    0.64
     inspirations
    0.64
     ۳
    0.63
    isé
    0.62
     templates
    0.61
     clues
    0.61
    POSITIVE LOGITS
     Would
    0.83
     WOULD
    0.74
     যদি
    0.72
    would
    0.72
     cosidd
    0.72
    Would
    0.71
     Pokud
    0.69
     If
    0.69
     Bagaimana
    0.68
     pokud
    0.68
    Act Density 0.001%

    No Known Activations