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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    巡
    -0.07
     Marlins
    -0.07
    ancock
    -0.06
    ohan
    -0.06
     requ
    -0.06
     gridColumn
    -0.06
     testcase
    -0.06
    _WS
    -0.06
    -trash
    -0.06
    GameOver
    -0.06
    POSITIVE LOGITS
    ause
    0.07
     …
    0.07
    _response
    0.07
     nuanced
    0.06
     Spatial
    0.06
    GR
    0.06
    Editar
    0.06
    ारन
    0.06
    Behavior
    0.06
     regularization
    0.06
    Act Density 0.015%

    No Known Activations