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

    Neuronpedia

    INDEX
    Explanations

    override func, slight offset, community by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Loyalty
    0.39
    Factory
    0.39
    Panic
    0.39
     surgically
    0.38
    Integration
    0.38
    र्ट
    0.37
     Mapping
    0.37
    OrCreate
    0.37
    Mean
    0.36
    Split
    0.36
    POSITIVE LOGITS
    젊
    0.39
    یم
    0.39
    avises
    0.38
    text
    0.38
    nfasis
    0.38
    χι
    0.37
     realism
    0.37
    rceil
    0.36
     plików
    0.36
    旖
    0.35
    Act Density 0.000%

    No Known Activations