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

    Neuronpedia

    INDEX
    Explanations

    Mr/Mrs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ard
    -0.07
     çünkü
    -0.07
     financing
    -0.07
    ائف
    -0.07
    .Payment
    -0.06
     acidic
    -0.06
    	current
    -0.06
     missionary
    -0.06
     censorship
    -0.06
     Gand
    -0.06
    POSITIVE LOGITS
    ::$_
    0.07
    ㇻ
    0.07
    实业
    0.07
    -sw
    0.07
    师事务所
    0.07
     LSM
    0.07
    元素
    0.06
     الثق
    0.06
     Null
    0.06
    (Context
    0.06
    Act Density 0.005%

    No Known Activations