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

    Neuronpedia

    INDEX
    Explanations

    exhibiting behaviors or traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    というのが
    0.46
     बनानी
    0.45
     berpeng
    0.44
    Render
    0.43
     एक्सपीरियंस
    0.42
     ощу
    0.42
    rendre
    0.40
    usingCamera
    0.40
    RENDER
    0.40
    ]={"
    0.40
    POSITIVE LOGITS
     signs
    0.96
     symptoms
    0.93
     behaviors
    0.90
     признаки
    0.85
     behaviours
    0.83
     behavior
    0.82
     traits
    0.79
     behaviour
    0.77
    signs
    0.77
     Signs
    0.75
    Act Density 0.013%

    No Known Activations