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

    Neuronpedia

    INDEX
    Explanations

    explaining simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isVideoRecording
    0.40
     পর্যালোচনা
    0.39
     Analysis
    0.39
     বিবে
    0.39
     analyze
    0.38
     Exchequer
    0.38
    Analysis
    0.38
     analysis
    0.37
    碌
    0.37
     rifless
    0.37
    POSITIVE LOGITS
     simplified
    1.46
     simplification
    1.37
     Simplified
    1.34
     simpl
    1.34
     simplifying
    1.33
    simplified
    1.32
    Simplified
    1.29
     simplify
    1.28
    Simpl
    1.27
     layman
    1.26
    Act Density 0.191%

    No Known Activations