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

    Neuronpedia

    INDEX
    Explanations

    implied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brigade
    -0.07
    ujících
    -0.06
     Bing
    -0.06
    Warm
    -0.06
     GestureDetector
    -0.06
     calm
    -0.06
     Cannes
    -0.06
    iệc
    -0.06
    Việc
    -0.06
     Consultant
    -0.06
    POSITIVE LOGITS
     implied
    0.07
     shaped
    0.06
     corporation
    0.06
    組織
    0.06
    \Requests
    0.06
    rud
    0.06
     escapes
    0.06
    ISED
    0.06
     %↵↵
    0.06
     assign
    0.06
    Act Density 0.002%

    No Known Activations