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

    Neuronpedia

    INDEX
    Explanations

    Nas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三种职业
    -0.07
    .sendStatus
    -0.07
    bid
    -0.07
     Mane
    -0.07
    สอน
    -0.06
    审计
    -0.06
    /msg
    -0.06
    elm
    -0.06
    malloc
    -0.06
     critically
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ყ
    0.07
    	offset
    0.06
     hearts
    0.06
     noisy
    0.06
    ива
    0.06
    											↵
    0.06
     equipos
    0.06
     Slovak
    0.06
     throughout
    0.06
    Act Density 0.002%

    No Known Activations