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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Did
    -0.07
    ’↵
    -0.06
    ↵↵↵↵↵↵↵↵↵
    -0.06
     why
    -0.06
    Usu
    -0.06
     LIS
    -0.06
     abruptly
    -0.06
    -fields
    -0.06
    节
    -0.06
    被
    -0.06
    POSITIVE LOGITS
     запас
    0.07
    ั
    0.07
    	Session
    0.07
    .drawString
    0.07
    	mysql
    0.07
    ?>>
    0.07
    lical
    0.06
     slun
    0.06
    ณฑ
    0.06
     Calgary
    0.06
    Act Density 0.068%

    No Known Activations