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

    Neuronpedia

    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uds
    0.29
    很有
    0.28
    cay
    0.27
     Suggestions
    0.26
     Deaths
    0.26
     Included
    0.25
     Series
    0.25
    很
    0.25
     Very
    0.25
    AU
    0.24
    POSITIVE LOGITS
     evidenced
    0.54
    sembles
    0.41
     opposed
    0.39
    cribable
    0.36
     exemplified
    0.35
    ides
    0.34
     amply
    0.34
     evin
    0.33
    ymmetric
    0.33
     well
    0.32
    Act Density 0.014%

    No Known Activations