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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hci
    0.54
    pointB
    0.53
    Gameplay
    0.52
     нәрсә
    0.52
    Valve
    0.50
     एमटीएस
    0.50
     ['(?
    0.50
    Bathroom
    0.50
    REGIUNE
    0.49
    ggbb
    0.49
    POSITIVE LOGITS
     declaration
    0.47
     model
    0.45
     siger
    0.45
     viste
    0.44
     declared
    0.44
    z
    0.43
     critique
    0.42
     v
    0.42
     Declaration
    0.41
     escape
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.