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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ูง
    -0.07
    	mysql
    -0.07
     �
    -0.07
     ignorance
    -0.06
     �
    -0.06
     Кол
    -0.06
    .Send
    -0.06
     caliber
    -0.06
     Buccane
    -0.06
    ंप
    -0.06
    POSITIVE LOGITS
    裂
    0.07
    	plt
    0.07
     mood
    0.07
     части
    0.06
     později
    0.06
    _wrapper
    0.06
    _MEMORY
    0.06
     anim
    0.06
    827
    0.06
     فصل
    0.06
    Act Density 0.000%

    No Known Activations