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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    irit
    -0.07
     Ca
    -0.07
     tic
    -0.07
     mer
    -0.07
     Walton
    -0.06
    -members
    -0.06
     Global
    -0.06
     ส
    -0.06
    㰀
    -0.06
     dare
    -0.06
    POSITIVE LOGITS
    замен
    0.07
    喧
    0.07
    exc
    0.07
    啸
    0.07
    กำหนด
    0.07
    此外
    0.07
    验收
    0.07
    _mesh
    0.07
     Wrap
    0.07
    wój
    0.06
    Act Density 0.001%

    No Known Activations