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

    Neuronpedia

    INDEX
    Explanations

    any construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dependencies
    0.43
     Error
    0.42
     Syntax
    0.41
    Latency
    0.41
     Bias
    0.40
     Timestamp
    0.40
     Encoding
    0.40
     Render
    0.40
     Payload
    0.40
     Debug
    0.39
    POSITIVE LOGITS
     international
    0.46
     socalled
    0.46
     chemical
    0.46
    elerinin
    0.46
     traditional
    0.46
     الْ
    0.45
     large
    0.44
     cultural
    0.44
     scientific
    0.44
     electrical
    0.43
    Act Density 6.734%

    No Known Activations