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

    Neuronpedia

    INDEX
    Explanations

    Caution/risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identifies
    -0.07
    `;↵
    -0.07
     Control
    -0.07
     control
    -0.07
     western
    -0.07
    %@
    -0.07
     fruit
    -0.07
     Rodrigo
    -0.07
     yellow
    -0.06
    (View
    -0.06
    POSITIVE LOGITS
     aa
    0.07
    Da
    0.06
    uyệ
    0.06
     showcasing
    0.06
    ,index
    0.06
    Career
    0.06
     showcased
    0.06
    emarks
    0.06
    (ob
    0.06
    	settings
    0.06
    Act Density 0.056%

    No Known Activations