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

    Neuronpedia

    INDEX
    Explanations

    malware/malicious attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.07
     compressed
    -0.07
    _reordered
    -0.06
     morb
    -0.06
     Dry
    -0.06
     BA
    -0.06
     scri
    -0.06
    resden
    -0.06
     shed
    -0.06
     DVD
    -0.06
    POSITIVE LOGITS
     shortly
    0.07
    しよう
    0.07
    ukarı
    0.07
     {//
    0.06
    willReturn
    0.06
     öz
    0.06
    ateurs
    0.06
    miyor
    0.06
     досвід
    0.06
    (Seq
    0.06
    Act Density 0.015%

    No Known Activations