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

    Neuronpedia

    INDEX
    Explanations

    served in roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inside
    0.81
     Inside
    0.73
    秆
    0.71
     strtok
    0.68
    Inside
    0.68
    αιο
    0.68
     எதிர்ப்பு
    0.67
     זי
    0.67
     때문
    0.67
     include
    0.65
    POSITIVE LOGITS
    学び
    0.83
    प्रिय
    0.80
     lokalen
    0.78
     опыт
    0.75
    监理
    0.75
     নায়
    0.73
     experiências
    0.72
     дос
    0.72
     locais
    0.70
     apprais
    0.70
    Act Density 0.000%

    No Known Activations