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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	set
    -0.07
    Summary
    -0.07
     ­
    -0.07
    BA
    -0.06
    	char
    -0.06
    	T
    -0.06
    ])/
    -0.06
     ]↵↵
    -0.06
     "*
    -0.06
    _mm
    -0.06
    POSITIVE LOGITS
    (Packet
    0.07
     Jeans
    0.07
     검
    0.06
     couple
    0.06
     Yah
    0.06
     Shaft
    0.06
    _Null
    0.06
    (link
    0.06
     الخط
    0.06
     potions
    0.06
    Act Density 0.030%

    No Known Activations