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

    Neuronpedia

    INDEX
    Explanations

    testing frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regenerated
    0.40
     reposition
    0.40
     electorate
    0.37
     kier
    0.37
    ウォ
    0.36
     immunoglobulin
    0.36
    اسى
    0.36
     ellipse
    0.35
     conceive
    0.35
     settled
    0.35
    POSITIVE LOGITS
     Tools
    0.50
     Testing
    0.49
     Framework
    0.49
    Framework
    0.48
    框架
    0.48
    framework
    0.47
    Tools
    0.46
     frameworks
    0.45
    Testing
    0.45
     framework
    0.43
    Act Density 0.001%

    No Known Activations