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

    Neuronpedia

    INDEX
    Explanations

    HTML meta viewport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tagging
    0.40
    TAG
    0.39
     tags
    0.38
    忤
    0.38
    都不
    0.37
     setText
    0.37
     annotations
    0.36
    AlignedText
    0.36
     hypoxic
    0.36
     TAG
    0.35
    POSITIVE LOGITS
    viewport
    0.44
    google
    0.42
    chrome
    0.42
     paul
    0.38
    aula
    0.38
    ne
    0.36
     google
    0.36
     Paulo
    0.35
    nep
    0.35
    nes
    0.35
    Act Density 0.001%

    No Known Activations