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

    Neuronpedia

    INDEX
    Explanations

    jobs and recruiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WA
    -0.07
     efter
    -0.07
     billionaires
    -0.07
    Topics
    -0.07
    /Y
    -0.07
    tanggal
    -0.07
     Harley
    -0.06
     defendants
    -0.06
    unifu
    -0.06
    Barrier
    -0.06
    POSITIVE LOGITS
     attributed
    0.06
     khiển
    0.06
    �
    0.06
    -variable
    0.06
    091
    0.06
     responsibility
    0.06
     时
    0.06
    					
↵
    0.06
     entrega
    0.05
    _Tool
    0.05
    Act Density 0.028%

    No Known Activations