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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     முழுவதும்
    0.41
     Endurance
    0.38
     erasing
    0.38
     sebuah
    0.38
     العديد
    0.38
     অসাধারণ
    0.38
     मोठ्या
    0.36
     पश्चात
    0.36
     Fatigue
    0.36
     außergewöhn
    0.36
    POSITIVE LOGITS
    approved
    0.40
    Polic
    0.39
    ського
    0.38
    nearby
    0.38
     nearby
    0.36
    already
    0.35
     גי
    0.35
    she
    0.35
    ської
    0.35
    Checked
    0.35
    Act Density 0.026%

    No Known Activations