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

    Neuronpedia

    INDEX
    Explanations

    in terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    꼴
    0.74
     dalam
    0.72
     એવી
    0.71
    በት
    0.70
     ため
    0.68
     behind
    0.67
     in
    0.67
     way
    0.67
     conversely
    0.66
     साथ
    0.64
    POSITIVE LOGITS
     specified
    0.87
    ☬
    0.86
     ønsk
    0.82
     യാത്ര
    0.78
     vorgesehen
    0.77
    ><%=
    0.77
     অপরাধ
    0.76
    sila
    0.76
    指定的
    0.76
    🍠
    0.74
    Act Density 0.211%

    No Known Activations