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

    Neuronpedia

    INDEX
    Explanations

    illegal or unethical things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LoopBlend
    0.43
     Blessing
    0.43
    陌
    0.43
    ig
    0.41
    O
    0.40
    apple
    0.39
     Bless
    0.39
     dimers
    0.39
    ar
    0.39
     Selfie
    0.39
    POSITIVE LOGITS
     notor
    0.50
     aktu
    0.46
     fraude
    0.44
    年在
    0.44
     ആരോപ
    0.43
     defamatory
    0.42
     incor
    0.42
     betrayed
    0.42
     പ്രസി
    0.42
    funding
    0.41
    Act Density 0.006%

    No Known Activations