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

    Neuronpedia

    INDEX
    Explanations

    malware

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of malware family names (tokens like “NAME_1” introduced after words such as “called” or “named”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ими
    -0.08
    NAS
    -0.06
    Movie
    -0.06
     defin
    -0.06
     heroine
    -0.06
    tc
    -0.06
     locate
    -0.06
     legal
    -0.06
     curator
    -0.06
    альной
    -0.06
    POSITIVE LOGITS
    tain
    0.07
    otten
    0.06
     Annunci
    0.06
     vaping
    0.06
     εισ
    0.06
     intelligence
    0.06
    ğit
    0.06
     prezident
    0.06
    _sn
    0.06
     mHandler
    0.06
    Act Density 0.009%

    No Known Activations