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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (Room
    -0.07
     Websites
    -0.07
     arisen
    -0.06
     BCHP
    -0.06
     upgraded
    -0.06
    אים
    -0.06
    keypress
    -0.06
     upgrades
    -0.06
    atisch
    -0.06
     услуг
    -0.06
    POSITIVE LOGITS
    컷
    0.08
    撮
    0.07
    .Version
    0.07
    纵横
    0.07
    .reducer
    0.07
    وق
    0.07
    .sav
    0.07
    _simulation
    0.07
    .primary
    0.07
    _rot
    0.07
    Act Density 0.008%

    No Known Activations