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

    Neuronpedia

    INDEX
    Explanations

    best interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Satisf
    0.43
    ualan
    0.41
    Satisf
    0.40
    Human
    0.37
     قان
    0.37
     Mundo
    0.36
     ቀ
    0.36
     There
    0.36
    挨
    0.36
    尬
    0.35
    POSITIVE LOGITS
     best
    1.29
    best
    1.27
     interests
    1.21
     Best
    1.13
    interests
    1.10
    Best
    1.09
     kepentingan
    1.00
    最佳
    1.00
     интере
    0.97
     बेस्ट
    0.97
    Act Density 0.008%

    No Known Activations