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

    Neuronpedia

    INDEX
    Explanations

    generative pre-trained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h4>
    1.11
    </h3>
    0.95
    vs
    0.90
    defaults
    0.90
    }):
    0.90
    /:
    0.88
    }:
    0.88
    url
    0.87
    params
    0.87
     «
    0.87
    POSITIVE LOGITS
     Development
    1.46
     Reduction
    1.32
     Management
    1.31
     Analyzer
    1.30
     Enhancement
    1.28
     Solutions
    1.26
     Selector
    1.24
     Engagement
    1.24
     Connector
    1.23
     Gathering
    1.23
    Act Density 0.557%

    No Known Activations