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

    Neuronpedia

    INDEX
    Explanations

    mm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sparkle
    -0.07
    帝
    -0.07
    Respons
    -0.06
    	java
    -0.06
    ورية
    -0.06
     تشکیل
    -0.06
     مراجع
    -0.06
    xffffffff
    -0.06
    	Returns
    -0.06
    ору
    -0.06
    POSITIVE LOGITS
     Canadians
    0.07
     Neuro
    0.06
     O
    0.06
     Joey
    0.06
    dex
    0.06
    ainen
    0.06
    -direction
    0.06
    出し
    0.06
     Hip
    0.06
    Unauthorized
    0.06
    Act Density 0.001%

    No Known Activations