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

    Neuronpedia

    INDEX
    Explanations

    European languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    既然
    -0.07
    �
    -0.07
     сиг
    -0.07
    ือ
    -0.07
    문을
    -0.07
    MM
    -0.07
     σε
    -0.07
    (',')
    -0.06
    -то
    -0.06
    хів
    -0.06
    POSITIVE LOGITS
     autorelease
    0.08
     cleans
    0.07
     rainbow
    0.07
    -->
↵
    0.07
     iv
    0.06
     mails
    0.06
    efault
    0.06
    nothrow
    0.06
    .fetchone
    0.06
    >"↵
    0.06
    Act Density 0.106%

    No Known Activations