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

    Neuronpedia

    INDEX
    Explanations

    ordinal number followed by a unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </td>
    0.45
     dalších
    0.43
     ancestors
    0.43
     humans
    0.39
     další
    0.39
     changes
    0.38
     contraindicated
    0.36
    zesz
    0.36
    сель
    0.36
     नए
    0.36
    POSITIVE LOGITS
     कॉंग्रेस
    0.42
     اسٹ
    0.41
    迪士尼
    0.41
     stint
    0.40
    綰
    0.40
    驄
    0.40
    𝖠
    0.39
    Ꮬ
    0.39
     Disney
    0.38
    ्युन
    0.38
    Act Density 0.007%

    No Known Activations