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

    Neuronpedia

    INDEX
    Explanations

    technical documents or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الكبير
    -0.07
    吸烟
    -0.07
    كبر
    -0.06
    몃
    -0.06
     undermines
    -0.06
    Micro
    -0.06
    ㉱
    -0.06
     bak
    -0.06
    שוב
    -0.06
    앚
    -0.06
    POSITIVE LOGITS
    岱
    0.07
     PDO
    0.07
    xab
    0.07
    温情
    0.07
     completeness
    0.07
    (errno
    0.07
    anceled
    0.07
     amounts
    0.07
    韵
    0.07
    𝑨
    0.07
    Act Density 0.001%

    No Known Activations