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

    Neuronpedia

    INDEX
    Explanations

    rl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     북
    -0.07
    ंज
    -0.06
    illin
    -0.06
    assing
    -0.06
     tộc
    -0.06
     explored
    -0.06
    捷
    -0.06
            
    -0.06
     earm
    -0.06
     Morrison
    -0.06
    POSITIVE LOGITS
    bl
    0.07
    Simple
    0.07
    DBNull
    0.07
     отли
    0.06
    て
    0.06
     litres
    0.06
     часто
    0.06
    mAh
    0.06
     Simple
    0.06
    ίος
    0.06
    Act Density 0.001%

    No Known Activations