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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nicolas
    -0.08
     بهره
    -0.08
     player
    -0.08
     joueur
    -0.08
     monde
    -0.07
     bénéf
    -0.07
     Sliding
    -0.07
    auche
    -0.07
    _PLAYER
    -0.07
    .Gui
    -0.07
    POSITIVE LOGITS
    要求
    0.10
     requirements
    0.10
     требований
    0.10
    Requirements
    0.10
     specifications
    0.10
     Requirements
    0.10
     요구
    0.09
     Specifications
    0.09
     requiring
    0.09
    Specifications
    0.09
    Act Density 0.071%

    No Known Activations