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

    Neuronpedia

    INDEX
    Explanations

    focus on specific aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यूँ
    0.38
    দর্শ
    0.36
     বলেও
    0.35
    くなり
    0.35
    ANGAN
    0.35
    avlja
    0.35
     यूं
    0.34
    Κ
    0.34
     अंदाजा
    0.34
    一一
    0.34
    POSITIVE LOGITS
     focus
    3.30
    focus
    3.09
     fokus
    3.05
     focusing
    2.92
    Focus
    2.89
     focuses
    2.89
     focussing
    2.78
     Focus
    2.72
     Fokus
    2.64
     Focusing
    2.59
    Act Density 0.063%

    No Known Activations