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

    Neuronpedia

    INDEX
    Explanations

    disagreement or argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    司
    -0.06
    里面
    -0.06
     απο
    -0.06
     रखन
    -0.06
     玩
    -0.06
     badge
    -0.06
     состоит
    -0.06
     Islamist
    -0.06
    ATORS
    -0.06
     सम
    -0.06
    POSITIVE LOGITS
    [:]
    0.07
     marketed
    0.06
    ůže
    0.06
     INTERRUPTION
    0.06
    	Task
    0.06
    bootstrap
    0.06
     Town
    0.06
    riet
    0.06
    lasyon
    0.06
     taxing
    0.06
    Act Density 0.031%

    No Known Activations