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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ละ
    -0.07
    .override
    -0.07
    >Error
    -0.07
    'aut
    -0.07
    붓
    -0.07
    _even
    -0.06
    😋
    -0.06
    身心
    -0.06
     عام
    -0.06
    _timezone
    -0.06
    POSITIVE LOGITS
     sometimes
    0.07
     sequentially
    0.07
    ilen
    0.07
     IPT
    0.07
    ᴏ
    0.07
     Dabei
    0.07
     clients
    0.07
     contraception
    0.07
    vided
    0.06
     максимально
    0.06
    Act Density 0.013%

    No Known Activations