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

    Neuronpedia

    INDEX
    Explanations

    Realization/recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мог
    -0.06
     Accum
    -0.06
     Democr
    -0.06
     coffin
    -0.06
     miners
    -0.06
    анню
    -0.06
     battle
    -0.06
     Programming
    -0.06
     enterprise
    -0.06
     vowels
    -0.06
    POSITIVE LOGITS
    砲
    0.07
    CRM
    0.07
    MouseListener
    0.07
    refs
    0.07
     которых
    0.07
    mpz
    0.07
    _ylabel
    0.07
    ُه
    0.06
     carpets
    0.06
     ガ
    0.06
    Act Density 0.071%

    No Known Activations