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

    Neuronpedia

    INDEX
    Explanations

    job description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )});
    0.44
     tumble
    0.43
     cherry
    0.42
    }~
    0.42
     bescherm
    0.41
     lubrication
    0.41
     protection
    0.41
     pager
    0.40
     restoration
    0.40
     wij
    0.40
    POSITIVE LOGITS
     शर्तें
    0.43
    規
    0.41
     умова
    0.40
    formas
    0.39
    seas
    0.39
    法定
    0.38
     조건을
    0.38
    bahan
    0.38
    條件
    0.37
    રસ
    0.37
    Act Density 0.002%

    No Known Activations