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

    Neuronpedia

    INDEX
    Explanations

    Interviews/Conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قم
    -0.06
    macros
    -0.06
    陸
    -0.06
    자료
    -0.06
    Farm
    -0.06
    dam
    -0.06
     tents
    -0.06
    �
    -0.06
    bsite
    -0.06
    参考
    -0.06
    POSITIVE LOGITS
    (Label
    0.07
     thee
    0.07
     sprayed
    0.06
    ออนไลน
    0.06
     investigates
    0.06
    byname
    0.06
     writable
    0.06
     bye
    0.06
    indx
    0.06
     clicks
    0.06
    Act Density 0.091%

    No Known Activations