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

    Neuronpedia

    INDEX
    Explanations

    reduces confusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flexibly
    0.31
     🌱
    0.30
     equipped
    0.29
     fulfils
    0.29
     biocompat
    0.28
    㦣
    0.28
     sensory
    0.28
     lineages
    0.28
     densely
    0.27
    🉑
    0.27
    POSITIVE LOGITS
     perjury
    0.34
     notoriety
    0.34
    Variance
    0.32
     dinero
    0.31
     vendedor
    0.30
     normaal
    0.30
    Mexico
    0.30
    Federal
    0.29
     jamais
    0.29
    Florida
    0.29
    Act Density 0.001%

    No Known Activations