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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    	else
    -0.06
    .'),↵
    -0.06
    (cx
    -0.06
     Shield
    -0.06
    _caps
    -0.06
     Fallon
    -0.06
    пов
    -0.06
    Filtered
    -0.06
    ुव
    -0.06
    POSITIVE LOGITS
    sterdam
    0.06
     Gerard
    0.06
    WL
    0.06
     Panel
    0.06
    073
    0.06
    newsletter
    0.06
     Federal
    0.06
     Стар
    0.06
    -week
    0.06
     bay
    0.06
    Act Density 0.000%

    No Known Activations