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

    Neuronpedia

    INDEX
    Explanations

    "'Hello World' examples"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    1.56
    =(\
    1.53
     apoi
    1.52
     dredged
    1.52
    ionale
    1.49
    ：（
    1.49
     lobe
    1.48
    ra
    1.47
    ievements
    1.44
     nouns
    1.44
    POSITIVE LOGITS
    ы
    1.61
    Hydrogen
    1.41
    ের
    1.40
    цю
    1.37
    Goodbye
    1.28
    ूट
    1.28
     Semiconductor
    1.26
     goodbye
    1.25
    hydrogen
    1.23
     maturity
    1.22
    Act Density 0.133%

    No Known Activations