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

    Neuronpedia

    INDEX
    Explanations

    technical passages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uploader
    -0.07
    ıyord
    -0.07
     Orient
    -0.07
     our
    -0.07
     Nhưng
    -0.07
     mình
    -0.06
     ener
    -0.06
    にして
    -0.06
    表现出
    -0.06
    你們
    -0.06
    POSITIVE LOGITS
    水泵
    0.08
     UIAlertAction
    0.08
    IgnoreCase
    0.07
    	ResultSet
    0.07
     offsetX
    0.07
    嗝
    0.07
    க
    0.07
    .utf
    0.07
     hamburg
    0.07
     WARRANTY
    0.07
    Act Density 9.841%

    No Known Activations