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

    Neuronpedia

    INDEX
    Explanations

    document everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.53
    车
    0.50
    also
    0.49
    т
    0.49
    ية
    0.47
    ेडकर
    0.47
    ToBe
    0.47
    මාණය
    0.47
    枓
    0.46
    Tens
    0.46
    POSITIVE LOGITS
     ਸੰ
    0.48
     digestion
    0.45
    拡散
    0.43
     isotropic
    0.43
     singularity
    0.43
    laughter
    0.41
     singularities
    0.41
    য়াছে
    0.40
     diffusive
    0.40
     uninhab
    0.40
    Act Density 0.042%

    No Known Activations