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

    Neuronpedia

    INDEX
    Explanations

    descriptive labels and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ডিজিটাল
    0.40
    デジタル
    0.39
     যেন
    0.39
     कोणी
    0.39
     parola
    0.37
     yang
    0.37
    که
    0.36
     خیال
    0.36
     separa
    0.36
     ڪري
    0.36
    POSITIVE LOGITS
    itur
    0.37
     Haut
    0.36
    Combining
    0.36
     అవి
    0.35
    itzen
    0.35
     থাকিত
    0.35
     lotions
    0.35
    লাল
    0.35
    ansen
    0.34
     الوسط
    0.34
    Act Density 0.000%

    No Known Activations