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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     декабря
    -0.08
     VLAN
    -0.07
     sinks
    -0.07
     currentDate
    -0.07
     sexual
    -0.06
    	matrix
    -0.06
    ीब
    -0.06
     hyp
    -0.06
    hexdigest
    -0.06
    國際
    -0.06
    POSITIVE LOGITS
    Highest
    0.07
     الحل
    0.06
    arer
    0.06
    (params
    0.06
     khởi
    0.06
     khối
    0.06
    ognitive
    0.06
     Contributor
    0.06
    outside
    0.06
    лось
    0.06
    Act Density 0.000%

    No Known Activations